{ "data": { "a": { "slug": "ming-3-0-audio-flash", "name": "Ming-3.0-audio-flash", "vendor": "inclusionAI (Ant Group)", "vendorUrl": "https://www.inclusion-ai.org", "kind": "weights", "category": "speech-to-text", "summary": "Ming-3.0-audio-flash is inclusionAI's open-weight audio-language model for Chinese and English. It takes audio with text instructions and returns transcripts, answers about the audio, or spoken replies, 126B parameters with 6.5B active, under MIT.", "url": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash", "markdownUrl": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ming-3-0-audio-flash.json", "dns": "ming-3-0-audio-flash.grade.anchorterminal.com", "repo": "https://huggingface.co/inclusionAI/Ming-3.0-audio-flash", "license": "MIT", "transports": [], "packages": [ { "registry": "huggingface", "name": "inclusionAI/Ming-3.0-audio-flash" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-21). ModelScope carries the same model under inclusionAI's organisation.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under MIT. inclusionAI sells no per-call access to these weights. Running them costs the hardware, 259.4 GB of BF16 files and eight 80 GB GPUs in inclusionAI's 128K serving profile (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://github.com/inclusionAI/Ming-3.0-audio-flash", "capabilities": [ "speech.stt", "speech.batch", "speech.languages", "voice.speech-to-speech", "model.open-weights" ], "tags": [ "open-weights", "speech-to-text", "audio-understanding", "speech-to-speech", "voice-cloning", "moe", "mit", "safetensors", "chinese", "english", "self-hosted", "new" ], "lastRelease": "2026-10-20", "graded": true, "anchor": { "graded": true, "score": 42.5, "grade": "E", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 32, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 65, "reach": 25, "risk": 50, "upkeep": 49 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "Ming-3.0-audio-flash is a cousin for Chinese and English transcription, questions about long audio and spoken replies in built-in or cloned voices, under MIT. It needs about 260 GB on a multi-GPU server, with inclusionAI's own runtime branches or Transformers remote code. The main risks are running repository code to load it and no published safety results.", "bestFor": "Teams with a multi-GPU server who want Chinese and English transcription, audio understanding and spoken replies from one MIT model", "strengths": [ "MIT with no use policy, downloadable with no account or gate", "Transcription, audio question answering and spoken replies from one model, with 484 built-in voices and voice cloning", "Request and response format documented for its vLLM-Omni and SGLang servers, with example clients and streamed audio", "131,072-token context with no position scaling and thinking switched on per request", "Repository, examples and runtime branch updated daily up to 20 October 2026" ], "weaknesses": [ "259.3 GB of BF16 files and no quantised build, so it needs a multi-GPU server and doesn't fit 128 GB", "No named runtime runs it from released code, it needs inclusionAI's fork branches or trust_remote_code", "No hosted provider, so an agent without the hardware can't call it", "No safety results, training data, limitations or knowledge cut-off published", "No timestamps or JSON transcript output, and where reasoning text returns isn't documented" ], "agentNotes": [ "Start it with inclusionAI's recipe, `hf download inclusionAI/Ming-3.0-audio-flash --local-dir inclusionAI/Ming-3.0-audio-flash \u0026\u0026 export MODEL_PATH=\"$PWD/inclusionAI/Ming-3.0-audio-flash\" \u0026\u0026 pip install -r requirements-vllm-omni.txt \u0026\u0026 MING_OUTPUT_MODE=asr ./scripts/serve_vllm_omni.sh \"$MODEL_PATH\"`, run from a clone of github.com/inclusionAI/Ming-3.0-audio-flash", "The 128K profile uses tensor parallelism over eight 80 GB H800 GPUs, the SGLang profile four and SGLang-Omni's cookbook two. It doesn't fit the 107.4 GB reference machine", "Use `MING_OUTPUT_MODE=asr` with the validated prompt and greedy decoding for transcripts, and split the language label from the text at the tab", "Use `MING_OUTPUT_MODE=text` for audio questions and the Talker profile with `modalities=[\"text\", \"audio\"]` for spoken replies", "Send audio as a base64 data URL in an `audio_url` item for vLLM-Omni, or as `input_audio` for SGLang", "Pick a voice with `audio.voice` and an id, or clone one with `ref_audio` and its exact `prompt_text`, never both", "Turn thinking on per request with `chat_template_kwargs` `{\"enable_thinking\": true}`, it's off by default and the reasoning comes back in think tags", "Tool calls follow the template's `\u003ctool_call\u003e` with `\u003carg_key\u003e` and `\u003carg_value\u003e` pairs, and no parser is named, so parse them yourself", "Review the repository's Python and the talker/ code, .pyc files included, before loading with trust_remote_code" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 42.5 } ], "editorialScores": { "interface": 65, "reach": 25, "risk": 50, "upkeep": 49 }, "provenanceScore": 61, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# inclusionAI's recipe, from github.com/inclusionAI/Ming-3.0-audio-flash (eight 80 GB GPUs for 128K)\nhf download inclusionAI/Ming-3.0-audio-flash --local-dir inclusionAI/Ming-3.0-audio-flash\nexport MODEL_PATH=\"$PWD/inclusionAI/Ming-3.0-audio-flash\"\npip install -r requirements-vllm-omni.txt\nMING_OUTPUT_MODE=asr ./scripts/serve_vllm_omni.sh \"$MODEL_PATH\"", "http": "python examples/vllm_omni_audio_chat.py examples/audio/introduce_ant_group.wav \\\n --task asr \\\n --prompt 'Please recognize the language of this speech and transcribe it, placing a `\\t` between the identified language and the transcribe.' \\\n --max-tokens 256 --no-repeat-ngram-size 10" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/ming-3-0-audio-flash" }, "sameCompany": [ "ming-3-0-asr-tiny", "ming-3-0-audio-tiny", "ming-3-0-tts-tiny", "lbs-27b", "ling-3-0-tiny", "ling-3-1-flash-1019" ], "weights": { "trainedBy": "inclusionAI (Ant Group)", "params": "126B", "active": "6.5B", "context": 131072, "goodFor": "Audio-language model for Chinese and English: speech to text, questions about audio and spoken replies.", "runtimes": [], "builds": [ { "name": "Ming-3.0-audio-flash", "url": "https://huggingface.co/inclusionAI/Ming-3.0-audio-flash", "who": "publisher", "precision": "bf16", "sizeGB": 259.3, "memoryGB": 512, "format": "safetensors", "note": "Main checkpoint 256.4 GB plus the Talker and VAE 3.0 GB" } ], "run": "hf download inclusionAI/Ming-3.0-audio-flash --local-dir inclusionAI/Ming-3.0-audio-flash \u0026\u0026 export MODEL_PATH=\"$PWD/inclusionAI/Ming-3.0-audio-flash\" \u0026\u0026 pip install -r requirements-vllm-omni.txt \u0026\u0026 MING_OUTPUT_MODE=asr ./scripts/serve_vllm_omni.sh \"$MODEL_PATH\"", "runBuild": "Ming-3.0-audio-flash", "checked": "2026-10-21", "minMemoryGB": 512 }, "family": { "lab": "inclusionAI (Ant Group)", "family": "Ming 3.0", "url": "https://www.anchorterminal.com/open-weights/#inclusionai", "others": [ { "name": "Ming-3.0-tts-0.5B", "url": "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B", "params": "0.5B (dense)", "listing": "https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b" }, { "name": "Ming-3.0-tts-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-tts-tiny", "params": "7.9B total, about 1.3B active (backbone)", "listing": "https://www.anchorterminal.com/tools/ming-3-0-tts-tiny" }, { "name": "Ming-3.0-audio-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny", "params": "9.3B total, 2.7B active", "listing": "https://www.anchorterminal.com/tools/ming-3-0-audio-tiny" }, { "name": "Ming-3.0-asr-tiny", "url": "https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny", "params": "not stated on the card (Hub metadata counts 8,865,800,992 in the files)", "listing": "https://www.anchorterminal.com/tools/ming-3-0-asr-tiny" } ], "olderCount": 54 }, "alsoIn": [ "voice-agents" ], "area": "voice", "provenance": { "legalEntity": "inclusionAI, Ant Group (named in the inclusion-ai.org footer; no registered company named)", "domain": "inclusion-ai.org", "domainRegistered": "2025-04-03", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/inclusionAI/Ming-3.0-audio-flash/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "inclusion-ai.org (inclusionai.github.io redirects there) describes inclusionAI as founded by Ant Group and links its Hugging Face and GitHub organisations. Its footer reads © 2026 inclusionAI, Ant Group. RDAP gives the domain's registration as 3 April 2025.", "Nothing is hosted, so the MIT licence stands in for terms of service and no privacy policy is scored.", "The changelog is the GitHub repository's commit history, whose messages mostly say what changed (a vLLM-Omni fix branch, voice selection, deployment profiles). The Hugging Face history mixes these with card layout edits.", "inclusion-ai.org/.well-known/security.txt answers with the site's 404 page, so there is none.", "Ant Group runs a company-wide security response centre, AntSRC (https://security.alipay.com/, read on 21 October 2026). Nothing on inclusionAI's card or sites links it." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ming-3-0-audio-flash.json", "live": { "slug": "ming-3-0-audio-flash", "securityTxt": { "url": "https://inclusion-ai.org/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-10T16:09:19.556283743Z" }, "domain": { "domain": "inclusion-ai.org", "registered": "2025-04-03", "source": "https://rdap.publicinterestregistry.org/rdap/domain/inclusion-ai.org", "checkedAt": "2026-11-08T15:01:29.637357411Z" }, "updatedAt": "2026-11-10T16:09:19.556283743Z" } }, "answer": "Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Ming-3.0-audio-flash's 42.5 (E), and leads in every scored category.", "b": { "slug": "nemotron-3-5-transcribe-30b-a4b", "name": "Nemotron 3.5 Transcribe 30B-A4B", "vendor": "NVIDIA", "vendorUrl": "https://github.com/NVIDIA-NeMo/Speech", "kind": "weights", "category": "speech-to-text", "summary": "Nemotron 3.5 Transcribe is NVIDIA's open-weight speech model of 30B parameters, about 4.3B active, that transcribes and translates recordings up to an hour in 40 languages, with speaker tags and word timestamps. OpenMDW-1.1. The 4-bit build fits 32 GB.", "url": "https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b", "markdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-transcribe-30b-a4b.json", "dns": "nemotron-3-5-transcribe-30b-a4b.grade.anchorterminal.com", "repo": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B", "license": "OpenMDW-1.1", "transports": [], "packages": [ { "registry": "huggingface", "name": "nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B" }, { "registry": "huggingface", "name": "nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8" }, { "registry": "huggingface", "name": "nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The BF16, FP8 and NVFP4 repositories are not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under OpenMDW-1.1, a permissive licence with no use policy or threshold. Running it yourself costs the hardware: 21.6 GB at 4 bits (NVFP4), 34.7 GB in FP8 or 67.5 GB in BF16. DeepInfra serves it for those without a GPU (checked 2026-11-10).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B", "capabilities": [ "speech.stt", "speech.batch", "speech.languages", "speech.diarisation", "speech.translation", "model.open-weights" ], "tags": [ "open-weights", "model", "speech-to-text", "asr", "multilingual", "translation", "diarization", "timestamps", "long-form", "moe", "reasoning", "openmdw", "safetensors", "fp8", "nvfp4", "self-hosted" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 20, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 85, "reach": 75, "risk": 75, "upkeep": 77 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "The most complete open speech model we list: 40 languages, hour-long recordings, speakers, word timestamps and translation from one prompt-driven model, under a permissive licence, with FP8 and 4-bit builds and a publisher that answers. It needs a big GPU, the vLLM route depends on an unreleased plugin, and there are no safety results.", "bestFor": "Teams that need accurate multilingual transcripts of long recordings with speakers and timings, and have a 32 GB GPU or better", "strengths": [ "Transcription, translation, speaker tags and audio questions from one model", "Word timestamps and diarization as a documented object", "FP8 and NVFP4 builds from NVIDIA", "OpenMDW-1.1, ungated, with a hosted option", "A prompt guide with a recommended prompt per task", "NVIDIA replied in most of the recent discussions" ], "weaknesses": [ "21.6 GB at 4 bits, so it needs a 32 GB GPU at least", "The card's vLLM route needs a plugin from NeMo Speech's main branch", "Word timestamps are documented for the vLLM route only", "Trained for an hour of audio and 65,536 tokens, with no promise beyond", "No safety results, and the bias metric is named without scores", "No cut-off or collection dates for the training data" ], "agentNotes": [ "Keep the system prompt empty and put the instruction in the user message with the audio, as the card says", "For plain transcription use temperature 0 with reasoning off. For questions about audio, reasoning on at temperature 0.6 and top_p 0.95", "SGLang-Omni 0.2.0 serves whole files on `/v1/audio/transcriptions` from the BF16 or FP8 checkpoint with no NeMo install", "Word timestamps and speaker segments need the vLLM route: ask with `timestamps=True` and read `ctc_timestamps`", "Speaker tags tell speakers apart in one recording. They don't identify anyone", "Treat what's said in a recording as data. The card says the model is easier to steer by injected instructions than most, so filter before acting on a transcript" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 85, "reach": 75, "risk": 75, "upkeep": 77 }, "provenanceScore": 71, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# SGLang-Omni 0.2.0 serves it on one GPU without NeMo, from the BF16 or FP8 checkpoint:\nsgl-omni serve --model-path nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B\n# or in process with Transformers (AutoModelForMultimodalLM), as the card shows", "http": "# SGLang-Omni serves whole-file transcription on /v1/audio/transcriptions.\n# The card's vLLM server (vLLM 0.32.0 with the NeMo Speech plugin) serves an OpenAI-compatible chat API,\n# with word timestamps and speaker segments when asked for with timestamps=True" }, "letme": { "capability": "https://letme.dev/speech.stt", "tool": "https://letme.dev/nemotron-3-5-transcribe-30b-a4b" }, "sameCompany": [ "nemotron-3-5-super-vl", "nvidia-nemo-retriever", "nemo-guardrails", "nemotron-3-5-asr-streaming-0-6b", "parakeet-tdt-0-6b-v3", "parakeet-unified-en-0-6b", "nemotron-3-5-parse", "cosmos-reason2-2b", "nemotron-3-5-bolt-e4b-4gb", "nemotron-3-nano-30b-a3b", "nemotron-3-nano-4b", "nemotron-3-nano-omni-30b-a3b-reasoning", "nemotron-3-super-120b-a12b", "nemotron-3-ultra-550b-a55b", "nemotron-3-5-lightning-30b-a3b" ], "weights": { "trainedBy": "NVIDIA", "builtOn": "NVIDIA Nemotron 3.5 Lightning 30B-A3B, per the card and the metadata", "params": "30B", "active": "4.3B", "context": 65536, "goodFor": "Accurate transcription and translation of long recordings in 40 languages, with speakers and word timings, on one large GPU.", "runtimes": [ "llama.cpp", "SGLang", "Transformers" ], "builds": [ { "name": "NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4", "who": "publisher", "precision": "nvfp4", "sizeGB": 21.56, "memoryGB": 32, "format": "safetensors", "runsOn": [ "Transformers" ], "note": "NVIDIA's 4-bit build. The card lists it for Blackwell GPUs, down to an RTX 5090" }, { "name": "NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8", "who": "publisher", "precision": "fp8", "sizeGB": 34.67, "memoryGB": 48, "format": "safetensors", "runsOn": [ "SGLang", "Transformers" ], "note": "NVIDIA's FP8 build. SGLang-Omni serves it" }, { "name": "NVIDIA-Nemotron-3.5-Transcribe-30B-A4B (BF16)", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B", "who": "publisher", "precision": "bf16", "sizeGB": 67.5, "memoryGB": 96, "format": "safetensors", "runsOn": [ "llama.cpp", "SGLang", "Transformers" ], "note": "The reference checkpoint, for accuracy and fine-tuning. The one layout llama.cpp converts" } ], "run": "sgl-omni serve --model-path nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8", "runBuild": "NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8", "checked": "2026-11-10", "minMemoryGB": 32 }, "family": { "lab": "NVIDIA (Nemotron)", "family": "Nemotron 3", "url": "https://www.anchorterminal.com/open-weights/#nvidia", "others": [ { "name": "Nemotron 3 Nano 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "params": "30B total, 3B active (31.6B per the safetensors index)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-30b-a3b" }, { "name": "Nemotron 3 Nano 30B-A3B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron 3 Super 120B-A12B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "params": "120B total, 12B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-super-120b-a12b" }, { "name": "Nemotron 3 Super 120B-A12B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16", "params": "120B total, 12B active" }, { "name": "Nemotron 3 Nano 4B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16", "params": "4B", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-4b" }, { "name": "Nemotron 3 Nano Omni 30B-A3B Reasoning", "url": "https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "params": "30B total, 3B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning" }, { "name": "Nemotron 3 Ultra 550B-A55B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "params": "550B total, 55B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b" }, { "name": "Nemotron 3 Ultra 550B-A55B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16", "params": "550B total, 55B active" }, { "name": "Nemotron 3 Ultra 550B-A55B GenRM", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-GenRM", "params": "550B total, 55B active" }, { "name": "Nemotron 3.5 Lightning 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "params": "30B total, 3B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-lightning-30b-a3b" }, { "name": "Nemotron 3.5 Lightning 30B-A3B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron 3.5 Super VL 120B-A12B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16", "params": "120B total, 12B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl" }, { "name": "Nemotron 3.5 Super VL 120B-A12B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16", "params": "120B total, 12B active" }, { "name": "Nemotron 3.5 Bolt 74B-A9B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16", "params": "74B total, 9B active" }, { "name": "Nemotron 3.5 Bolt E4B 4GB", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB", "params": "8B total, 4B effective", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb" }, { "name": "Nemotron Labs 3 Elastic 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron Labs 3 Puzzle 75B-A9B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16", "params": "75B total, 9B active" }, { "name": "Nemotron 3 Labs Ultra Math SFT", "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-SFT", "params": "550B total, 55B active" }, { "name": "Nemotron 3 Labs Ultra Math RL", "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-RL", "params": "550B total, 55B active" }, { "name": "Nemotron Labs 3 Competitive Coding 550B-A55B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Competitive-Coding-550B-A55B-NVFP4", "params": "550B total, 55B active" }, { "name": "nemotron-3.5-asr-streaming-0.6b", "url": "https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b", "params": "0.6B (638M per the safetensors count)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b" }, { "name": "Nemotron 3.5 Parse", "url": "https://huggingface.co/nvidia/Nemotron-3.5-Parse", "params": "0.631B (630,800,496 trainable parameters per the card)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-parse" } ], "olderCount": 47 }, "area": "voice", "provenance": { "legalEntity": "NVIDIA Corporation", "domain": "nvidia.com", "domainRegistered": "1993-04-20", "endpointOnVendorDomain": null, "terms": "https://openmdw.ai/license/1-1/", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The model sits in NVIDIA's Hugging Face organisation and the card's governing terms are OpenMDW-1.1. The domain registration date is carried from the RDAP check made for nemotron-3-nano-30b-a3b on 21 October 2026.", "Nothing is hosted under this listing, so the licence stands in for terms of service and no privacy policy is scored.", "The changelog is the commit history, 13 commits from 27 to 29 October 2026.", "security.txt is carried from our other NVIDIA listings and wasn't re-read." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b.json" }, "edges": [ { "by": 50, "category": "reach", "leads": "nemotron-3-5-transcribe-30b-a4b", "name": "Reach", "reasons": { "a": "Memory earns 0, because the only build is inclusionAI's BF16 release at 259.3 GB, and a fifth on top is 311.2 GB, above the 256 GB band. Runtimes earn 0, since no named runtime runs the audio model from its own released code. Transformers needs the repository's remote code, vLLM and SGLang need inclusionAI's fork branches, vLLM-Omni and SGLang-Omni aren't on the list, and llama.cpp, Ollama and LM Studio don't have it. Builds earn 0 with BF16 only. Terms earn 15 for MIT with nothing added. Download earns 10, since the repository isn't gated. Hosted earns 0, with no inference provider on its Hugging Face page, none on OpenRouter and no inclusionAI API for it.", "b": "Memory 20, the smallest build is NVIDIA's NVFP4 repository, 21.56 GB, and 21.56 GB × 1.2 = 25.9 GB, within 32 GB. FP8 is 34.67 GB and BF16 67.5 GB. Runtimes 15, Released Transformers 5.22.2 has the nemotron3_5_transcribe model (5). Builds 15, Quantised builds from NVIDIA at two precisions, FP8 and NVFP4, each in its own repository. Terms 10, OpenMDW-1.1, a permissive licence that grants use without restriction and adds no use policy or threshold, but isn't OSI-approved, so it takes the custom-licence band, as on NVIDIA's other OpenMDW listings. Download 10, the Hub API reports gated false for all three repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, the card gives a release on build.nvidia.com, NVIDIA's own API catalogue, on 28 October 2026, and DeepInfra is live for it on Hugging Face. 20 + 15 + 15 + 10 + 10 + 5 = 75." }, "scores": { "a": 25, "b": 75 } }, { "by": 28, "category": "upkeep", "leads": "nemotron-3-5-transcribe-30b-a4b", "name": "Documentation and upkeep", "reasons": { "a": "The model card earns 14, covering five of the seven points and missing limitations and a knowledge cut-off. Training data earns 0, with nothing described. Last change earns 20, with the voice interface, examples and inclusionAI's runtime branch all changed between 18 and 20 October 2026. Responsiveness earns 0, because nobody has asked a question yet in the Hugging Face discussions and GitHub issues couldn't be counted. Version policy earns 5 for a first release in its own repository. File health earns 10, with config, tokenizer, template and card in agreement and no broken-file report waiting.", "b": "Model card 17, Intended use, limitations (the explainability subcard's technical limitations), the architecture, the parameters, the context and the languages are on the card. Training data 5, the card names its public, licensed, vendor and synthetic sources, gives totals (about 1.72 million hours and 5.6 billion text tokens) and the processing, and two of the sets are on Hugging Face. Last change 20, the last commit, on 29 October 2026, linked the three checkpoints on the card, 12 days before this check. Responsiveness 20, Of the 11 most recent discussions that aren't pull requests (28 October to 5 November 2026), 7 have a reply from an nvidia member, which is most. Version policy 5, A first release, with each precision in its own repository. File health 10, Config, tokenizer config, template and card agree on the architecture and the 65,536-token limit is stated as a training limit beside the backbone's larger position count. 17 + 5 + 20 + 20 + 5 + 10 = 77." }, "scores": { "a": 49, "b": 77 } }, { "by": 25, "category": "risk", "leads": "nemotron-3-5-transcribe-30b-a4b", "name": "Risk", "reasons": { "a": "File safety earns 15, safetensors weights with no pickle files, less 10 because loading needs trust_remote_code and speech output imports Python from the model directory, which also ships compiled .pyc files. Provenance earns 15, files in inclusionAI's own organisation, linked from its site, and a checksum on every file. Safety evaluation earns 0, with none published. Agent guidance earns 0, since the only caution is about reviewing code before loading it. Licence risk keeps 15 under plain MIT. The security programme earns 5 for Ant Group's AntSRC reporting centre, read as a company-wide route the way Google's was for Gemma, while advisories handled in public weren't found or couldn't be checked on GitHub.", "b": "File safety 25, safetensors only in all three repositories, no .bin, .pt or .pth files and no Python. Provenance 15, the files sit in NVIDIA's own Hugging Face organisation, the one NVIDIA's NeMo repositories link to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results. Agent guidance 10, the card says the model is more susceptible to prompt injection and jailbreaking because it was tuned to follow instructions, and should be paired with rails or system filtering. Licence risk 15, OpenMDW-1.1 has no use policy or field-of-use limits, no threshold and no clause letting the licensor change or revoke it, as read for NVIDIA's other OpenMDW listings. Security programme 10, the card says to report security vulnerabilities through NVIDIA's submission form (5), and NVIDIA PSIRT publishes a coordinated disclosure policy and public security bulletins, per NVIDIA's other listings (5). 25 + 15 + 0 + 10 + 15 + 10 = 75." }, "scores": { "a": 50, "b": 75 } }, { "by": 20, "category": "interface", "leads": "nemotron-3-5-transcribe-30b-a4b", "name": "Agent interface", "reasons": { "a": "This model has a chat interface with function calls as well as speech, so the tool-calling line is read for its tool calls, as for Ming-3.0-audio-tiny, and structured output for what it returns. The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 10, because function tools are declared and returned only as the template says, with no parser named, though inclusionAI's README documents the audio requests and replies for its vLLM-Omni and SGLang servers. Trained tool calling earns 20 from inclusionAI's own tool-calling sample and a template that renders several calls in one turn. Structured output earns 5, since the transcript form and audio format are documented but no timestamps or JSON output are. Reasoning control earns 0, because thinking switches per request but where its text comes back isn't documented. Context earns 10 for 131,072 tokens with no scaling.", "b": "Chat template 20, chat_template.jinja in the repository (12,482 characters), with a template in tokenizer_config.json too. Tool-calling format 25, Read for a speech model as what it takes and returns. Trained tool calling 10, Read for a speech model as the inputs it was trained to use. Structured output 15, Read for a speech model as typed outputs. Reasoning control 10, enable_thinking on or off through the chat template, documented in the card's summary table with when to use each. Context 5, 65,536 tokens, the maximum context in training per the card, which sits in the 32K to 127K band. 20 + 25 + 10 + 15 + 10 + 5 = 85." }, "scores": { "a": 65, "b": 85 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "inclusionAI (Ant Group)", "b": "NVIDIA", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "OpenMDW-1.1", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-20", "b": "2026-10-29", "name": "Last release" }, { "a": "no document linked", "b": "not read yet", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "2.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Ming-3.0-audio-flash's 42.5 (E), and leads in every scored category.", "question": "Which is better for AI agents, Ming-3.0-audio-flash or Nemotron 3.5 Transcribe 30B-A4B?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Teams with a multi-GPU server who want Chinese and English transcription, audio understanding and spoken replies from one MIT model", "slug": "ming-3-0-audio-flash", "watchFor": "259.3 GB of BF16 files and no quantised build, so it needs a multi-GPU server and doesn't fit 128 GB" }, { "aheadOn": [ "Reach, 75 against 25", "Risk, 75 against 50", "Agent interface, 85 against 65", "Documentation and upkeep, 77 against 49" ], "also": null, "goodFor": "Teams that need accurate multilingual transcripts of long recordings with speakers and timings, and have a 32 GB GPU or better", "slug": "nemotron-3-5-transcribe-30b-a4b", "watchFor": "21.6 GB at 4 bits, so it needs a 32 GB GPU at least" } ], "history": null, "job": { "capability": "speech.stt", "name": "Speech-to-text" }, "others": [ { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-flash.json", "title": "Cohere Transcribe 03-2026 vs Ming-3.0-audio-flash", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-flash" }, { "json": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Cohere Transcribe 03-2026 vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-flash.json", "title": "Granite Speech 5.0 2B vs Ming-3.0-audio-flash", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-flash" }, { "json": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Granite Speech 5.0 2B vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-ming-3-0-audio-flash.json", "title": "Ming-3.0-asr-tiny vs Ming-3.0-audio-flash", "url": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-ming-3-0-audio-flash" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Ming-3.0-asr-tiny vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-ming-3-0-audio-tiny.json", "title": "Ming-3.0-audio-flash vs Ming-3.0-audio-tiny", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-ming-3-0-audio-tiny" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-asr-streaming-0-6b.json", "title": "Ming-3.0-audio-flash vs Nemotron 3.5 ASR Streaming 0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-asr-streaming-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Ming-3.0-audio-flash vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-tdt-0-6b-v3.json", "title": "Ming-3.0-audio-flash vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-tdt-0-6b-v3" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-unified-en-0-6b.json", "title": "Ming-3.0-audio-flash vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-0-6b.json", "title": "Ming-3.0-audio-flash vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-1-7b.json", "title": "Ming-3.0-audio-flash vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Ming-3.0-audio-flash vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-underdog-bark-3.json", "title": "Ming-3.0-audio-flash vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-underdog-bark-3" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-voxtral-mini-4b-realtime-2602.json", "title": "Ming-3.0-audio-flash vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-voxtral-mini-4b-realtime-2602" }, { "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Ming-3.0-audio-tiny vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-nemotron-3-5-transcribe-30b-a4b.json", "title": "Nemotron 3.5 ASR Streaming 0.6B vs Nemotron 3.5 Transcribe 30B-A4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-nemotron-3-5-transcribe-30b-a4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-tdt-0-6b-v3.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Parakeet TDT 0.6B v3", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-tdt-0-6b-v3" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Parakeet Unified EN 0.6B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-0-6b.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-ASR-0.6B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-0-6b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-1-7b.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-ASR-1.7B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-1-7b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Underdog Bark 3.0", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602.json", "title": "Nemotron 3.5 Transcribe 30B-A4B vs Voxtral Mini 4B Realtime 2602", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 50, "edge": "nemotron-3-5-transcribe-30b-a4b", "key": "reach", "ming-3-0-audio-flash": 25, "name": "Reach", "nemotron-3-5-transcribe-30b-a4b": 75, "weight": 25 }, { "by": 25, "edge": "nemotron-3-5-transcribe-30b-a4b", "key": "risk", "ming-3-0-audio-flash": 50, "name": "Risk", "nemotron-3-5-transcribe-30b-a4b": 75, "weight": 20 }, { "by": 20, "edge": "nemotron-3-5-transcribe-30b-a4b", "key": "interface", "ming-3-0-audio-flash": 65, "name": "Agent interface", "nemotron-3-5-transcribe-30b-a4b": 85, "weight": 10 }, { "by": 28, "edge": "nemotron-3-5-transcribe-30b-a4b", "key": "upkeep", "ming-3-0-audio-flash": 49, "name": "Documentation and upkeep", "nemotron-3-5-transcribe-30b-a4b": 77, "weight": 10 } ], "summary": "Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Ming-3.0-audio-flash's 42.5 (E), and leads in every scored category. Both do speech-to-text.", "tasks": null, "tutorials": [], "verdicts": { "ming-3-0-audio-flash": "Ming-3.0-audio-flash is a cousin for Chinese and English transcription, questions about long audio and spoken replies in built-in or cloned voices, under MIT. It needs about 260 GB on a multi-GPU server, with inclusionAI's own runtime branches or Transformers remote code. The main risks are running repository code to load it and no published safety results.", "nemotron-3-5-transcribe-30b-a4b": "The most complete open speech model we list: 40 languages, hour-long recordings, speakers, word timestamps and translation from one prompt-driven model, under a permissive licence, with FP8 and 4-bit builds and a publisher that answers. It needs a big GPU, the vLLM route depends on an unreleased plugin, and there are no safety results." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b", "json": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b.min.md" }, "markdown": "Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Ming-3.0-audio-flash's 42.5 (E), and leads in every scored category. Both do speech-to-text.\n\n- Ming-3.0-audio-flash: grade E, 42.5/100, rank #157 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/ming-3-0-audio-flash.md · JSON https://www.anchorterminal.com/api/v1/tools/ming-3-0-audio-flash.json\n- Nemotron 3.5 Transcribe 30B-A4B: grade C, 61/100, rank #79 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b.md · JSON https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-transcribe-30b-a4b.json\n- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md\n- All 386 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md\n- Best conversational voice-agent APIs: https://www.anchorterminal.com/best/voice-agents/index.md\n- All 581 voice agents comparisons: https://www.anchorterminal.com/compare/voice-agents/index.md\n\n## Which one, for what\n\n### Ming-3.0-audio-flash (E)\n\nGood for: Teams with a multi-GPU server who want Chinese and English transcription, audio understanding and spoken replies from one MIT model\n\nWatch for: 259.3 GB of BF16 files and no quantised build, so it needs a multi-GPU server and doesn't fit 128 GB\n\n### Nemotron 3.5 Transcribe 30B-A4B (C)\n\nGood for: Teams that need accurate multilingual transcripts of long recordings with speakers and timings, and have a 32 GB GPU or better\n\nAhead on:\n- Reach, 75 against 25\n- Risk, 75 against 50\n- Agent interface, 85 against 65\n- Documentation and upkeep, 77 against 49\n\nWatch for: 21.6 GB at 4 bits, so it needs a 32 GB GPU at least\n\n\n## Why the edge\n\n### Reach: Nemotron 3.5 Transcribe 30B-A4B +50\n\n- Ming-3.0-audio-flash (25): Memory earns 0, because the only build is inclusionAI's BF16 release at 259.3 GB, and a fifth on top is 311.2 GB, above the 256 GB band. Runtimes earn 0, since no named runtime runs the audio model from its own released code. Transformers needs the repository's remote code, vLLM and SGLang need inclusionAI's fork branches, vLLM-Omni and SGLang-Omni aren't on the list, and llama.cpp, Ollama and LM Studio don't have it. Builds earn 0 with BF16 only. Terms earn 15 for MIT with nothing added. Download earns 10, since the repository isn't gated. Hosted earns 0, with no inference provider on its Hugging Face page, none on OpenRouter and no inclusionAI API for it.\n- Nemotron 3.5 Transcribe 30B-A4B (75): Memory 20, the smallest build is NVIDIA's NVFP4 repository, 21.56 GB, and 21.56 GB × 1.2 = 25.9 GB, within 32 GB. FP8 is 34.67 GB and BF16 67.5 GB. Runtimes 15, Released Transformers 5.22.2 has the nemotron3_5_transcribe model (5). Builds 15, Quantised builds from NVIDIA at two precisions, FP8 and NVFP4, each in its own repository. Terms 10, OpenMDW-1.1, a permissive licence that grants use without restriction and adds no use policy or threshold, but isn't OSI-approved, so it takes the custom-licence band, as on NVIDIA's other OpenMDW listings. Download 10, the Hub API reports gated false for all three repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, the card gives a release on build.nvidia.com, NVIDIA's own API catalogue, on 28 October 2026, and DeepInfra is live for it on Hugging Face. 20 + 15 + 15 + 10 + 10 + 5 = 75.\n\n### Documentation and upkeep: Nemotron 3.5 Transcribe 30B-A4B +28\n\n- Ming-3.0-audio-flash (49): The model card earns 14, covering five of the seven points and missing limitations and a knowledge cut-off. Training data earns 0, with nothing described. Last change earns 20, with the voice interface, examples and inclusionAI's runtime branch all changed between 18 and 20 October 2026. Responsiveness earns 0, because nobody has asked a question yet in the Hugging Face discussions and GitHub issues couldn't be counted. Version policy earns 5 for a first release in its own repository. File health earns 10, with config, tokenizer, template and card in agreement and no broken-file report waiting.\n- Nemotron 3.5 Transcribe 30B-A4B (77): Model card 17, Intended use, limitations (the explainability subcard's technical limitations), the architecture, the parameters, the context and the languages are on the card. Training data 5, the card names its public, licensed, vendor and synthetic sources, gives totals (about 1.72 million hours and 5.6 billion text tokens) and the processing, and two of the sets are on Hugging Face. Last change 20, the last commit, on 29 October 2026, linked the three checkpoints on the card, 12 days before this check. Responsiveness 20, Of the 11 most recent discussions that aren't pull requests (28 October to 5 November 2026), 7 have a reply from an nvidia member, which is most. Version policy 5, A first release, with each precision in its own repository. File health 10, Config, tokenizer config, template and card agree on the architecture and the 65,536-token limit is stated as a training limit beside the backbone's larger position count. 17 + 5 + 20 + 20 + 5 + 10 = 77.\n\n### Risk: Nemotron 3.5 Transcribe 30B-A4B +25\n\n- Ming-3.0-audio-flash (50): File safety earns 15, safetensors weights with no pickle files, less 10 because loading needs trust_remote_code and speech output imports Python from the model directory, which also ships compiled .pyc files. Provenance earns 15, files in inclusionAI's own organisation, linked from its site, and a checksum on every file. Safety evaluation earns 0, with none published. Agent guidance earns 0, since the only caution is about reviewing code before loading it. Licence risk keeps 15 under plain MIT. The security programme earns 5 for Ant Group's AntSRC reporting centre, read as a company-wide route the way Google's was for Gemma, while advisories handled in public weren't found or couldn't be checked on GitHub.\n- Nemotron 3.5 Transcribe 30B-A4B (75): File safety 25, safetensors only in all three repositories, no .bin, .pt or .pth files and no Python. Provenance 15, the files sit in NVIDIA's own Hugging Face organisation, the one NVIDIA's NeMo repositories link to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results. Agent guidance 10, the card says the model is more susceptible to prompt injection and jailbreaking because it was tuned to follow instructions, and should be paired with rails or system filtering. Licence risk 15, OpenMDW-1.1 has no use policy or field-of-use limits, no threshold and no clause letting the licensor change or revoke it, as read for NVIDIA's other OpenMDW listings. Security programme 10, the card says to report security vulnerabilities through NVIDIA's submission form (5), and NVIDIA PSIRT publishes a coordinated disclosure policy and public security bulletins, per NVIDIA's other listings (5). 25 + 15 + 0 + 10 + 15 + 10 = 75.\n\n### Agent interface: Nemotron 3.5 Transcribe 30B-A4B +20\n\n- Ming-3.0-audio-flash (65): This model has a chat interface with function calls as well as speech, so the tool-calling line is read for its tool calls, as for Ming-3.0-audio-tiny, and structured output for what it returns. The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 10, because function tools are declared and returned only as the template says, with no parser named, though inclusionAI's README documents the audio requests and replies for its vLLM-Omni and SGLang servers. Trained tool calling earns 20 from inclusionAI's own tool-calling sample and a template that renders several calls in one turn. Structured output earns 5, since the transcript form and audio format are documented but no timestamps or JSON output are. Reasoning control earns 0, because thinking switches per request but where its text comes back isn't documented. Context earns 10 for 131,072 tokens with no scaling.\n- Nemotron 3.5 Transcribe 30B-A4B (85): Chat template 20, chat_template.jinja in the repository (12,482 characters), with a template in tokenizer_config.json too. Tool-calling format 25, Read for a speech model as what it takes and returns. Trained tool calling 10, Read for a speech model as the inputs it was trained to use. Structured output 15, Read for a speech model as typed outputs. Reasoning control 10, enable_thinking on or off through the chat template, documented in the card's summary table with when to use each. Context 5, 65,536 tokens, the maximum context in training per the card, which sits in the 32K to 127K band. 20 + 25 + 10 + 15 + 10 + 5 = 85.\n\n## Score by category\n\n| Category | Weight | Ming-3.0-audio-flash | Nemotron 3.5 Transcribe 30B-A4B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 25 | 75 | Nemotron 3.5 Transcribe 30B-A4B +50 |\n| Risk | 20% (20 this run) | 50 | 75 | Nemotron 3.5 Transcribe 30B-A4B +25 |\n| Agent interface | 10% (10 this run) | 65 | 85 | Nemotron 3.5 Transcribe 30B-A4B +20 |\n| Documentation and upkeep | 10% (10 this run) | 49 | 77 | Nemotron 3.5 Transcribe 30B-A4B +28 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **42.5 · E** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Ming-3.0-audio-flash | Nemotron 3.5 Transcribe 30B-A4B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | inclusionAI (Ant Group) | NVIDIA |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | OpenMDW-1.1 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-20 | 2026-10-29 |\n| Terms last updated | no document linked | not read yet |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | 2.3/5 (4) | none |\n\n## Verdicts\n\n**Ming-3.0-audio-flash.** Ming-3.0-audio-flash is a cousin for Chinese and English transcription, questions about long audio and spoken replies in built-in or cloned voices, under MIT. It needs about 260 GB on a multi-GPU server, with inclusionAI's own runtime branches or Transformers remote code. The main risks are running repository code to load it and no published safety results.\n\n**Nemotron 3.5 Transcribe 30B-A4B.** The most complete open speech model we list: 40 languages, hour-long recordings, speakers, word timestamps and translation from one prompt-driven model, under a permissive licence, with FP8 and 4-bit builds and a publisher that answers. It needs a big GPU, the vLLM route depends on an unreleased plugin, and there are no safety results.\n\n## Before you call either\n\n### Ming-3.0-audio-flash\n\n1. Start it with inclusionAI's recipe, `hf download inclusionAI/Ming-3.0-audio-flash --local-dir inclusionAI/Ming-3.0-audio-flash \u0026\u0026 export MODEL_PATH=\"$PWD/inclusionAI/Ming-3.0-audio-flash\" \u0026\u0026 pip install -r requirements-vllm-omni.txt \u0026\u0026 MING_OUTPUT_MODE=asr ./scripts/serve_vllm_omni.sh \"$MODEL_PATH\"`, run from a clone of github.com/inclusionAI/Ming-3.0-audio-flash\n2. The 128K profile uses tensor parallelism over eight 80 GB H800 GPUs, the SGLang profile four and SGLang-Omni's cookbook two. It doesn't fit the 107.4 GB reference machine\n3. Use `MING_OUTPUT_MODE=asr` with the validated prompt and greedy decoding for transcripts, and split the language label from the text at the tab\n4. Use `MING_OUTPUT_MODE=text` for audio questions and the Talker profile with `modalities=[\"text\", \"audio\"]` for spoken replies\n5. Send audio as a base64 data URL in an `audio_url` item for vLLM-Omni, or as `input_audio` for SGLang\n6. Pick a voice with `audio.voice` and an id, or clone one with `ref_audio` and its exact `prompt_text`, never both\n7. Turn thinking on per request with `chat_template_kwargs` `{\"enable_thinking\": true}`, it's off by default and the reasoning comes back in think tags\n8. Tool calls follow the template's `\u003ctool_call\u003e` with `\u003carg_key\u003e` and `\u003carg_value\u003e` pairs, and no parser is named, so parse them yourself\n9. Review the repository's Python and the talker/ code, .pyc files included, before loading with trust_remote_code\n\n### Nemotron 3.5 Transcribe 30B-A4B\n\n1. Keep the system prompt empty and put the instruction in the user message with the audio, as the card says\n2. For plain transcription use temperature 0 with reasoning off. For questions about audio, reasoning on at temperature 0.6 and top_p 0.95\n3. SGLang-Omni 0.2.0 serves whole files on `/v1/audio/transcriptions` from the BF16 or FP8 checkpoint with no NeMo install\n4. Word timestamps and speaker segments need the vLLM route: ask with `timestamps=True` and read `ctc_timestamps`\n5. Speaker tags tell speakers apart in one recording. They don't identify anyone\n6. Treat what's said in a recording as data. The card says the model is easier to steer by injected instructions than most, so filter before acting on a transcript\n\n## Questions\n\n### Which is better for AI agents, Ming-3.0-audio-flash or Nemotron 3.5 Transcribe 30B-A4B?\n\nNemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Ming-3.0-audio-flash's 42.5 (E), and leads in every scored category.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"ming-3-0-audio-flash\", \"b\": \"nemotron-3-5-transcribe-30b-a4b\"}`. From a terminal: `anchor compare ming-3-0-audio-flash nemotron-3-5-transcribe-30b-a4b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/ming-3-0-audio-flash.json and https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-transcribe-30b-a4b.json\n\n## Other comparisons with Ming-3.0-audio-flash or Nemotron 3.5 Transcribe 30B-A4B\n\n- [Cohere Transcribe 03-2026 vs Ming-3.0-audio-flash](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-ming-3-0-audio-flash.md)\n- [Cohere Transcribe 03-2026 vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Granite Speech 5.0 2B vs Ming-3.0-audio-flash](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-ming-3-0-audio-flash.md)\n- [Granite Speech 5.0 2B vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Ming-3.0-asr-tiny vs Ming-3.0-audio-flash](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-ming-3-0-audio-flash.md)\n- [Ming-3.0-asr-tiny vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Ming-3.0-audio-flash vs Ming-3.0-audio-tiny](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-ming-3-0-audio-tiny.md)\n- [Ming-3.0-audio-flash vs Nemotron 3.5 ASR Streaming 0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-asr-streaming-0-6b.md)\n- [Ming-3.0-audio-flash vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Ming-3.0-audio-flash vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-tdt-0-6b-v3.md)\n- [Ming-3.0-audio-flash vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-parakeet-unified-en-0-6b.md)\n- [Ming-3.0-audio-flash vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-0-6b.md)\n- [Ming-3.0-audio-flash vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-1-7b.md)\n- [Ming-3.0-audio-flash vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Ming-3.0-audio-flash vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-underdog-bark-3.md)\n- [Ming-3.0-audio-flash vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-voxtral-mini-4b-realtime-2602.md)\n- [Ming-3.0-audio-tiny vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Nemotron 3.5 ASR Streaming 0.6B vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-nemotron-3-5-transcribe-30b-a4b.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-tdt-0-6b-v3.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-0-6b.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-1-7b.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3.md)\n- [Nemotron 3.5 Transcribe 30B-A4B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-11", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Ming-3.0-audio-flash vs Nemotron 3.5 Transcribe 30B-A4B", "url": "" } ], "description": "Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) to Ming-3.0-audio-flash's 42.5 (E) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Ming-3.0-audio-flash E 42.5", "Nemotron 3.5 Transcribe 30B-A4B C 61", "scores" ], "h1": "Ming-3.0-audio-flash vs Nemotron 3.5 Transcribe 30B-A4B", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b", "published": "2026-10-01", "section": "tools", "title": "Ming-3.0-audio-flash vs Nemotron 3.5 Transcribe 30B-A4B (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b" }, "tokens": { "markdown": 4650, "slim": 880 }, "version": 1 }