MI

Mistral Small 3.1 24B Instruct 2503

MistralGGUF by EnlistedGhostUpdated 2026-01-26
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant9.2 GB
Quick answer

Mistral Small 3.1 24B Instruct 2503 needs about 16.9 GB of memory at Q4_K_M (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 18 quants, from 9.2 GB (Q2_K_S) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral Small 3.1 24B Instruct 2503 – 24B parameter model with vision and 128k context

Mistral Small 3.1 24B Instruct 2503 is a 23.6 billion‑parameter instruction‑fine‑tuned model. It supports vision, a 128k token context window, and a Tekken tokenizer with 131k vocabulary. The model is licensed under Apache‑2.0.

Good at

  • Vision understanding
  • Long‑context instruction following
  • Multilingual text generation

Limits

  • No explicit vision support in quant list
  • Large memory requirement for high‑quality quants
  • No mention of GPU acceleration beyond llama.cpp

Best for

  • Local inference on RTX 4090 or 32 GB RAM
  • Sensitive data handling with local deployment
  • Fine‑tuning for domain expertise

Who it’s for. Developers and researchers needing a local, instruction‑oriented LLM with vision and long‑context capabilities. The model is suitable for hobbyists, organizations handling sensitive data, and enterprises that require a flexible, open‑licensed solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_S9.2 GB 11.1 GB
Too big Get file →
Q2_K10.1 GB 12.0 GB
Too big Get file →
Q3_K_S10.7 GB 12.5 GB
Too big Get file →
Q2_K_M11.0 GB 12.8 GB
Too big Get file →
Q2_K_L11.4 GB 13.3 GB
Too big Get file →
Q3_K_M11.7 GB 13.6 GB
Too big Get file →
Q2_K_XL12.4 GB 14.3 GB
Too big Get file →
Q3_K_L12.7 GB 14.5 GB
Too big Get file →
Q4_K_S13.6 GB 15.5 GB
Too big Get file →
Q3_K_XL14.0 GB 15.9 GB
Too big Get file →
Q4_K_M15.0 GB 16.9 GB
Too big Get file →
Q4_K_XL15.5 GB 17.3 GB
Too big Get file →
Q5_K_S16.4 GB 18.2 GB
Too big Get file →
Q5_K_M17.4 GB 19.3 GB
Too big Get file →
Q6_K19.3 GB 21.2 GB
Too big Get file →
Q5_K_XL19.4 GB 21.3 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 13.61 GB, estimated 15.5 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (15.05 GB, 16.9 GB memory) is suitable. For 16 GB VRAM, Q5_K_S (16.39 GB, 18.2 GB memory) provides higher quality. Memory estimates are approximate.

What GPU do you need for Mistral Small 3.1 24B Instruct 2503?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q2_K (10.1 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_XL (14.0 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_XL (19.4 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).

Which Mistral Small 3.1 24B Instruct 2503 quant should you choose?

Q4_K_M is the usual starting point for Mistral Small 3.1 24B Instruct 2503: it balances file size and quality well. Here it is a 15.0 GB file.

The Q8_0 file is 25.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K_S at 9.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byEnlistedGhost
FamilyMistral
Licenseapache-2.0
Downloads (HF)784
Last updated2026-01-26

Frequently asked questions about Mistral Small 3.1 24B Instruct 2503

How much VRAM does Mistral Small 3.1 24B Instruct 2503 need?

About 16.9 GB at Q4_K_M with an 8K context window. That is the 15.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Mistral Small 3.1 24B Instruct 2503 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Small 3.1 24B Instruct 2503 GGUF?

It depends on the quant: Q2_K_S is 9.2 GB, Q2_K is 10.1 GB, Q3_K_S is 10.7 GB, Q2_K_M is 11.0 GB, Q2_K_L is 11.4 GB, Q3_K_M is 11.7 GB and 12 more.

What context length does Mistral Small 3.1 24B Instruct 2503 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Mistral Small 3.1 24B Instruct 2503 GGUF?

The files are on Hugging Face in the EnlistedGhost/Mistral-Small-3.1-24B-Instruct-2503-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mistral Small 3.1 24B Instruct 2503 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on an RTX 4090 with 8 GB VRAM?

Use the Q4_K_S quant; it requires about 15.5 GB memory at 8k context, which exceeds 8 GB VRAM. A larger VRAM GPU is needed.

Does the model support vision tasks?

Yes, the model includes vision capabilities as noted in its parent model card.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of Mistral-Small-3.1-24B-Instruct-2503

Similar models

Browse all →

More from EnlistedGhost

All by EnlistedGhost →

More Mistral models

All Mistral →

Other medium models

All medium models →