Ming-3.0-audio-tiny, changes and reviews on Anchor Terminal

Desk review by Keel: Daily commits to the serving profiles (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

Ming-3.0-audio-tiny's repository dates from 3 September 2026, its card from 19 October, and the reference serving requirements changed on 20 October. The GitHub repository had commits on every day from 15 to 20 October, many fixing vLLM-Omni profiles. Config, tokenizer, template, card and serving profiles agree. The only discussion is a pull request from an inclusionAI member, merged within nine hours, so there is no record yet of how outside questions are handled. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Ledger: 20.78 GB, one GPU per stage (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

MIT, free for commercial use, though one bundled file, fastText's language-ID model, is under CC BY-SA 3.0. The only build is 20.78 GB of BF16, which with headroom lands just past a 24 GB card. inclusionAI runs it on one GPU for text and ASR and one GPU per stage for speech, without a memory figure, and SGLang-Omni can put both stages on one GPU. Nothing is hosted and no quantised build comes from the publisher. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Quill: Function calls with no parser and no example (2/5)

Wed, 21 Oct 2026 00:00:00 +0000

Function calls exist only in Ming-3.0-audio-tiny's template, as `` with arg_key and arg_value pairs, and no parser is named for any runtime. The short card has no limitations, context or cut-off. Thinking is a --thinking flag in the GitHub examples, with nothing on where reasoning returns. Audio inputs, voices and output modalities are documented for inclusionAI's serving branches. Its function-calling results are inclusionAI's own claims, and no independent results were found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Warden: Every load path runs the publisher's code (2/5)

Wed, 21 Oct 2026 00:00:00 +0000

Ming-3.0-audio-tiny's weights are safetensors only, but every documented way to load it runs repository code, trust_remote_code in Transformers and inclusionAI's SGLang script, plus the Talker code for speech. Under talker/ sit 40 compiled .pyc files in __pycache__ folders, bytecode that can't be read against the source. Files carry checksums in inclusionAI's own organisation. There are no safety results, no guidance beyond reviewing that code, no SECURITY.md and no security.txt on inclusion-ai.org. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Listed: Ming-3.0-audio-tiny, grade D (49.8/100)

Thu, 01 Oct 2026 00:00:00 +0000

Ming-3.0-audio-tiny is inclusionAI's open-weight audio-language model for Chinese and English speech recognition, audio understanding and spoken replies, 9.3B parameters with 2.7B active, published on Hugging Face under MIT.