Granite Speech 5.0 2B vs Ming-3.0-asr-tiny

Granite Speech 5.0 2B 95

Memory 30, the smallest build listed that keeps 4 bits is IBM's Q4_K_M GGUF, 1.14 GB with the 1.16 GB audio projector, and 2.30 GB × 1.2 = 2.8 GB, within 16 GB. IBM recommends Q8_0, 3.12 GB with the projector. Runtimes 20, Released Transformers 5.22.2 and vLLM 0.33.0 have the granite_speech model, llama.cpp b12242 has its converter and audio front end, and Ollama carries it as ibm/granite5-speech, which the card says was tested with v0.40.15. Builds 15, IBM publishes GGUF builds at fourteen quantised precisions, from Q2_K to Q8_0, with the audio projector. Terms 15, Apache 2.0 in the metadata and on the card, with nothing added. Download 10, the Hub API reports gated false for both repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, IBM runs a Hugging Face Inference Endpoint that serves this model through an OpenAI-compatible API, with the address and code on the card. 30 + 20 + 15 + 15 + 10 + 5 = 95.

Ming-3.0-asr-tiny 50

Memory earns 25 because the publisher's BF16 files are 17.7 GB, about 21.3 GB with the fifth added, which fits 24 GB. Runtimes score 0, since no released version of the six named runtimes has its own code for this model (Transformers v5.22.1, vLLM v0.33.0, SGLang v0.5.23, llama.cpp b12111, and Ollama v0.40.14 through its pinned llama.cpp b11963, read on 4 November). It loads through the publisher's remote code on Transformers 5.12.1 and is served by SGLang-Omni's main branch, a separate runtime. Builds score 0 because inclusionAI publishes no quantised build. MIT with nothing added gives terms the full 15 and the ungated repository gives download the full 10. Hosted too scores 0, as no inference provider is mapped on Hugging Face and no publisher API serves it. 25 + 0 + 0 + 15 + 10 + 0 = 50.

Granite Speech 5.0 2B 92

Model card 17, Intended use, limitations, the architecture, the size, the 16K positions and two-minute segments, and the languages are on the card. Training data 20, the data is listed with sources and sizes: a 39-row table giving each corpus, its task, its hours and a link to where it comes from, with the synthetic sets described. Last change 20, the last commit, on 6 November 2026, updated the card, 4 days before this check. Responsiveness 20, Both discussions that aren't pull requests (21 and 28 October 2026) have a reply from an ibm-granite member. Version policy 5, granite-speech-4.1-2b stays in its own repository and 5.0 came out in a new one, which names its predecessor and gives a release date. File health 10, Config, template and card agree on the architecture and the 16K positions. 17 + 20 + 20 + 20 + 5 + 10 = 92.

Ming-3.0-asr-tiny 61

The card covers intended use, limitations, architecture and languages, and misses parameters, context length and a cut-off (11). A training data summary added on 21 October 2026 names the mix (Common Crawl and other public sets, commercially licensed text and audio, Ant Spider crawls from March 2024 to May 2026, synthetic data from models such as Ling-lite, no user data), a latest collection date of about May 2026 and the filtering, with sizes only as ranges (15). The files last changed on 21 October 2026, 14 days before this check (20). The one discussion on Hugging Face, opened on 19 October, still has no reply from inclusionAI, and GitHub issues couldn't be counted (0). It's a first release (5), and the files agree with the card with no broken-file report waiting (10). 11 + 15 + 20 + 0 + 5 + 10 = 61.

Granite Speech 5.0 2B 70

File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in either repository. Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 10, the card says what the model does with a prompt it doesn't know: it ignores an unfamiliar or malformed prompt and transcribes, which it says limits how audio can steer the system. Licence risk 15, Apache 2.0 with no use policy, no threshold and no right to change the terms. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the Granite 4.2 3B listing on 4 November 2026 (5). 25 + 15 + 0 + 10 + 15 + 5 = 70.

Ming-3.0-asr-tiny 55

File safety gets 15, safetensors only but loaded with trust_remote_code. Provenance gets 15 for files in inclusionAI's own organisation, linked from its site, with hashes for every file. MIT carries none of the licence deductions, so licence risk keeps 15. Agent guidance gets 5 for the SGLang guide's general cautions about the unauthenticated server and untrusted logit processors. Safety evaluation scores 0, since no safety results exist. 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, with no advisories handled in public found. 15 + 15 + 0 + 5 + 15 + 5 = 55.

Granite Speech 5.0 2B 55

Chat template 20, chat_template.jinja in the repository (193 characters). 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 0, Read for a speech model as typed outputs. Reasoning control 0, A speech model with no reasoning. Context 0, the language model is extended to 16K positions, per the card and config.json (16,384), below the 32K band, and the card says to send audio in segments of about two minutes. 20 + 25 + 10 + 0 + 0 + 0 = 55.

Ming-3.0-asr-tiny 60

Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. The publisher documents the instruction, language hint, hotword and dialogue context, the language-tab-transcript output and the parser, and the SGLang-Omni request fields (25). It was trained to use context hints, one clip per request (10). JSON output and streaming are documented on the card with how to ask for them, though there are no timestamps or speaker labels (15). The chat template scores 10 because the shipped Jinja file isn't the documented prompt path, which is the publisher's processor code. Reasoning control and context score 0, with no reasoning to control and an 8,192-token context. 10 + 25 + 10 + 15 + 0 + 0 = 60.