https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602 Dated changes, score moves with their causes, what our workers noticed, and reviews for Voxtral Mini 4B Realtime 2602. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4095 https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4095 Wed, 21 Oct 2026 00:00:00 +0000 review Mistral dated this release in its name, 2602, and put the Arabic variant of 8 October 2026 in its own repository. The mistralai repository last changed on 11 March, and Mistral Experimental's GGUF files on 27 July. Mistral answered 16 of 39 discussions, none opened after 25 February. A report from 28 March that the Transformers path fails waits, and the card says vLLM only while documenting Transformers. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4096 https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4096 Wed, 21 Oct 2026 00:00:00 +0000 review Both routes are priced. Mistral's API serves the same model as voxtral-mini-transcribe-realtime-2602 at $0.006 per audio minute, or $6 per 1,000 minutes, a separate listing. Self-hosting needs one GPU with 16 GB or more for the 8.86 GB BF16 weights, per the card, and Mistral Experimental's Q4_K GGUF for audio.cpp is 3.1 GB. Apache 2.0, with one card line against infringing third parties' rights. Ungated. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4097 https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4097 Wed, 21 Oct 2026 00:00:00 +0000 review Mistral documents 16 kHz audio streamed over vLLM's realtime WebSocket endpoint and the transcription_delay_ms setting, with text decoded in Transformers. The card contradicts itself, saying only vLLM is supported while documenting Transformers, and giving delays starting at 80 ms and at 240 ms. No JSON, timestamps or diarisation are documented for the weights. The Open ASR Leaderboard records 8.44 English short-form WER and 9.36 multilingual, at an RTFx of 102.57. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4098 https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#rev_4098 Wed, 21 Oct 2026 00:00:00 +0000 review Voxtral Mini 4B Realtime 2602 loads from two safetensors files with vLLM or Transformers code and mistral-common for prompts, so nothing runs from the repository, and the verified mistralai organisation hashes every file. mistral.ai's security.txt names a contact and a HackerOne policy. The card's ExecuTorch link leads to Mistral Experimental, an unverified organisation where an audio-cpp account uploaded a GGUF. There are no safety results and nothing on untrusted audio. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602 https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Voxtral Mini 4B Realtime 2602 is Mistral AI's open-weight streaming speech recognition model, a causal audio encoder of about 970M parameters on a Ministral 3B decoder, 4.4B in all, transcribing 13 languages live under Apache 2.0.