Arxiv:2507.13264 De En Es Fr Hi It Mistral-common Nl Pt Region:us Safetensors Sharded Tensorflow Vllm Voxtral
Model Card on HF 🤗: https://huggingface.co/mistralai/Voxtral-Mini-3B-2507
Voxtral Mini 3B 2507 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Voxtral Mini 3B 2507 Parameters and Internals
| LLM Name | Voxtral Mini 3B 2507 |
| Repository 🤗 | https://huggingface.co/mistralai/Voxtral-Mini-3B-2507 |
| Model Size | 3b |
| Required VRAM | 9.4 GB |
| Updated | 2025-07-30 |
| Maintainer | mistralai |
| Model Files | |
| Supported Languages | en fr de es it pt nl hi |
| Model Architecture | MambaSSM |
| License | MNPL-0.1 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Vocabulary Size | 131072 |
Best Alternatives to Voxtral Mini 3B 2507
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...3.2 3B Instruct QLORA INT4 EO8 | 0K / GB | 253 | 68 |
| ...3B Instruct SpinQuant INT4 EO8 | 0K / GB | 361 | 37 |
Rank the Voxtral Mini 3B 2507 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 50230 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124