Leaderboard / Mistral AI
Voxtral Small 24B
Mistral AI · Voxtral · released 2025-07-15 · data checked 2026-11-01 Needs verification
Voxtral Small 24B is a 24B-parameter dense model from Mistral AI (Europe), released 2025-07-15 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 16.9 GB of memory at 4-bit with an 8K-token context and costs $0.15 per million tokens through the cheapest API provider.
Speech understanding (transcription, audio Q&A) on top of Mistral Small 3.
Benchmarks
Each bar shows this model's score. The tick marks the best medium model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- Mistral AI (FR · Europe)
- Architecture
- Dense transformer
- Total parameters
- 24B
- Active parameters
- All (dense)
- Size class
- Medium
- Context window
- 32K tokens
- Input modalities
- text, audio
- Reasoning
- Instruct (no thinking)
- License
- Apache-2.0
- Openness
- Open weights
- Memory to run
- ~16.9 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 12.7K downloads (30 days) · 556 likes
- API providers
- 1 on OpenRouter
- API price
- $0.10 in / $0.30 out per 1M (OpenRouter, 2026-11-03)
Compare with
- Voxtral Small 24B vs LFM2.5 24B-A2B (24B, index 61.4)
- Voxtral Small 24B vs Magistral Small 1.2 (24B, index 55.9)
- Voxtral Small 24B vs Mistral Small 3.2 (24B, index 38.6)
Sources
Something wrong here? Report it.
Run it locally
Uses bartowski/mistralai_Voxtral-Small-24B-2507-GGUF (Q4_K_M). Swap the tag for another size: BF16, IQ2_M, IQ2_S, IQ2_XS, IQ3_M, IQ3_XS, IQ3_XXS, IQ4_NL….
ollama run hf.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF:Q4_K_Mllama-server -hf bartowski/mistralai_Voxtral-Small-24B-2507-GGUF:Q4_K_Mvllm serve mistralai/Voxtral-Small-24B-2507Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context |
|---|---|---|
| 16-bit F16 | 50 GB | 54 GB |
| 8-bit Q8_0 | 27 GB | 32 GB |
| 4-bit Q4_K_M | 16 GB | 21 GB |