mistralai/Voxtral-Mini-4B-Realtime-2602
automatic-speech-recognition model by mistralai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Voxtral Mini 4B Realtime 2602 is a multilingual, realtime speech-transcription model and among the first open-source solutions to achieve accuracy comparable to offline systems with a delay of <500ms. It supports 13 languages and outperforms existing open-source baselines across a range of tasks, making it ideal for applications like voice assistants and live subtitling. Built with a natively streaming architecture and a custom causal audio encoder - it allows configurable transcription delays (240ms to 2.4s), enabling users to balance latency and accuracy based on their needs. At a 480ms delay, it matches the performance of leading offline open-source transcription models, as well as realtime APIs. As a 4B-parameter model, is optimized for on-device deployment, requiring minimal hardware resources. It runs in realtime with on devices minimal hardware with throughput exceeding 12.5 tokens/second. This model is released in BF16 under the Apache-2 license, ensuring flexibility for both research and commercial use.…
Read the full model card ↗ · Preview checked 2026-10-29T12:38:33.800Z
Inside the original model card — Document outline
- Voxtral Mini 4B Realtime 2602
- Key Features
- Use Cases
- Recommended Settings
- Benchmark Results
- Fleurs
- Long-form English
- Short-form English
- Usage
- vLLM (recommended)
- Installation
- Serve
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
mistralai/Voxtral-Mini-4B-Realtime-2602 is a automatic-speech-recognition model repository published by mistralai on Hugging Face. The source reports the vllm library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- automatic-speech-recognition
- Library
- vllm
- Recent downloads (30 days)
- 1,830,373
- Cumulative likes
- 1,054
- Hugging Face trending score
- 5
- Reported safetensors parameters
- 4,429,679,360
- Architecture
- VoxtralRealtimeForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-01-21T17:22:02.000Z
- Last modified
- 2026-03-11T15:04:02.000Z
Compatibility and lineage
Reported languages: en, fr, es, de, ru, zh, ja, it, pt, nl, ar, hi, ko
Reported base models: mistralai/Ministral-3-3B-Base-2512
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:32.899Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
jonatasgrosman/wav2vec2-large-xlsr-53-japanese