Mistral Small 3.1 24B
By Mistral AI · France
Updated 2026-07-13
Overview
Mistral AI's Small 3.1 — Small 3 plus a vision encoder, a 128k context, and ~150 tok/s inference under Apache 2.0. Small 3.2 (June 2025) is a drop-in upgrade.
When to pick this model
- Multimodal assistants needing both text and vision in one model
- Long-context RAG over mixed text and image sources
- Self-hosted Apache 2.0 deployments on a 24GB GPU
- High-throughput inference where latency matters
- Replacing separate text and vision models with a single 24B
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 14 GB |
| Q5_K_M | 17 GB |
| Q8_0 | 26 GB |
| FP16 (no quantization) | 48 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Mistral Small 3.1 24B needs a 16 GB card at Q4_K_M (14 GB). Stepping up to Q8_0 nearly doubles the footprint to 26 GB, and unquantized FP16 weights take 48 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Mistral Small 3.1 24B needs roughly 24 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 4 tokens/sec on entry-level GPUs, on the order of 15 tokens/sec on a mid-range card, and up to 40 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Mistral Small 3.1 24B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Mistral Small 3.1 24B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 14 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 14 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Q4_K_M (14 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q5_K_M (17 GB used) |
| 32 GB | RTX 5090 | Q8_0 (26 GB used) |
Which GPU should you buy to run Mistral Small 3.1 24B?
To run Mistral Small 3.1 24B locally at Q4, you need ~14 GB of VRAM. The best value for this is a RTX 5070 Ti (16 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Published benchmark scores
| Benchmark | Score |
|---|---|
| MMLU | 80.6 |
| MMMU | 64 |
Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.
To put Mistral Small 3.1 24B in context: its MMLU score of 80.6 ranks #9 of the 34 catalog models with a published MMLU result (catalog median 73.4); its MMMU score of 64 ranks #4 of the 8 catalog models with a published MMMU result (catalog median 62.8). Scores are author-published and measured under different harnesses, so treat gaps of a few points as noise rather than a verdict.
Strengths
- Vision and text combined in one 24B model
- 128k context window
- Apache 2.0 license
- Around 150 tokens/sec inference
Limitations
- Requires Ollama 0.6.5 or newer
- Small 3.2 (June 2025) is a marginal improvement worth picking instead
- Vision quality trails Qwen2-VL on OCR
Typical workloads
In our catalog grid, Mistral Small 3.1 24B is filed under Advanced Chat, Vision, Agents — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: vision-language work — screenshots, charts, scanned documents; multilingual workloads; French-language output where quality matters.
The 125k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: Dense · multimodal text+vision · Tekken tokenizer
Training: Successor to Small 3 with added visual encoding.
The best open-weight 24B multimodal model under Apache 2.0 — and Small 3.2 makes it slightly better still.
Quick start
ollama run mistral-small3.1:24bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Mistral Small 3.1 24B need?
At the recommended Q4_K_M quantization, Mistral Small 3.1 24B needs about 14 GB of VRAM. Q8_0 takes 26 GB, and unquantized FP16 weights take 48 GB.
Can Mistral Small 3.1 24B run without a GPU?
Yes — with roughly 24 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Mistral Small 3.1 24B support?
Mistral Small 3.1 24B supports a 125k-token context window (128,000 tokens).
Can I use Mistral Small 3.1 24B commercially?
Yes. Mistral Small 3.1 24B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Mistral Small 3.1 24B on consumer hardware?
Our compatibility engine estimates on the order of 15 tokens/sec on a mid-range GPU and up to 40 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Mistral Small 3.1 24B should I download first?
Start with Q4_K_M (14 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q5_K_M.