MI

Mistral-Small-3.1-24B-Instruct-2503

MistralGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant5.6 GB
Quick answer

Mistral-Small-3.1-24B-Instruct-2503 needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 37 quants, from 5.6 GB (TQ1_0) 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 – 24 billion‑parameter instruction model with vision and 128k context

Mistral‑Small‑3.1‑24B‑Instruct‑2503 is a 23.6 billion‑parameter model built on the Mistral architecture. It supports vision tasks and offers a 128k token context window. The model is released under the Apache 2.0 license.

Good at

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

Limits

  • No dedicated vision API – image handling via llama.cpp only
  • Requires 8k context for memory estimates
  • Large VRAM needed for higher‑bit quantizations

Best for

  • Chatbots needing image understanding
  • Document summarization with long context
  • Multilingual content creation

Who it’s for. Developers building instruction‑driven applications that require image input and extended context. The model is suitable for both research and commercial use under Apache 2.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_05.6 GB 7.5 GB
Tight Get file →
IQ1_S6.5 GB 8.4 GB
Too big Get file →
TQ2_06.7 GB 8.5 GB
Too big Get file →
IQ1_M7.0 GB 8.9 GB
Too big Get file →
IQ2_XXS7.4 GB 9.2 GB
Too big Get file →
IQ2_XS8.0 GB 9.8 GB
Too big Get file →
IQ2_S8.2 GB 10.1 GB
Too big Get file →
Q2_K_S8.4 GB 10.2 GB
Too big Get file →
IQ2_M8.7 GB 10.5 GB
Too big Get file →
Q2_K_M9.1 GB 11.0 GB
Too big Get file →
IQ3_XXS9.5 GB 11.4 GB
Too big Get file →
IQ3_XS10.0 GB 11.8 GB
Too big Get file →
IQ3_S10.5 GB 12.3 GB
Too big Get file →
IQ3_M10.6 GB 12.5 GB
Too big Get file →
Q3_K_S10.6 GB 12.5 GB
Too big Get file →
Q3_K_M11.6 GB 13.5 GB
Too big Get file →
IQ4_XS12.8 GB 14.6 GB
Too big Get file →
Q4_013.3 GB 15.1 GB
Too big Get file →
IQ4_NL13.5 GB 15.3 GB
Too big Get file →
Q4_K_S13.8 GB 15.7 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q4_114.7 GB 16.6 GB
Too big Get file →
BF1616.1 GB 17.9 GB
Too big Get file →
F1616.1 GB 17.9 GB
Too big Get file →
Q5_016.2 GB 18.1 GB
Too big Get file →
Q5_K_S16.6 GB 18.4 GB
Too big Get file →
Q5_K_M16.9 GB 18.7 GB
Too big Get file →
Q5_117.7 GB 19.5 GB
Too big Get file →
Q6_K_M19.3 GB 21.2 GB
Too big Get file →
BF1620.9 GB 22.8 GB
Too big Get file →
F1620.9 GB 22.8 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →
BF1626.3 GB 28.2 GB
Too big Get file →
F1626.3 GB 28.2 GB
Too big Get file →
BF1626.3 GB 28.2 GB
Too big Get file →
F1633.6 GB 35.4 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use TQ1_0 (5.63 GB file, 7.5 GB memory) or IQ1_S (6.52 GB file, 8.4 GB memory). If 12 GB VRAM is available, IQ2_XS (7.99 GB file, 9.8 GB memory) or Q2_K_S (8.39 GB file, 10.2 GB memory) provide better accuracy. Higher‑bit quantizations such as Q4_0 or BF16 require 15–28 GB VRAM.

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: the best quant that fits is TQ1_0 (5.6 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XS (10.0 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (20.9 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (26.3 GB file, about 28.2 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (33.6 GB file, about 35.4 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 14.3 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 TQ1_0 at 5.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

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 byMungert
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,264
Last updated2025-09-24

Frequently asked questions about Mistral-Small-3.1-24B-Instruct-2503

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

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 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?

Yes, with TQ1_0: the 5.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: TQ1_0 is 5.6 GB, IQ1_S is 6.5 GB, TQ2_0 is 6.7 GB, IQ1_M is 7.0 GB, IQ2_XXS is 7.4 GB, IQ2_XS is 8.0 GB and 31 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 Mungert/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 8 GB VRAM?

Yes, with TQ1_0 or IQ1_S quantizations, which fit within 8 GB VRAM and use about 7.5–8.4 GB memory at 8k context.

Does the model support image input?

Yes, the model includes vision capabilities and can process images via llama.cpp.

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-Base-2503

Similar models

Browse all →

More from Mungert

All by Mungert →

More Mistral models

All Mistral →

Other medium models

All medium models →