MI

Mistral Small 3.2 24B Instruct 2506

MistralGGUF by bartowskiUpdated 2025-12-19
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant6.5 GB
Quick answer

Mistral Small 3.2 24B Instruct 2506 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 27 quants, from 6.5 GB (IQ2_XXS) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

24‑Billion‑parameter Mistral Small 3.2 Instruct with vision support

Mistral Small 3.2 24B Instruct 2506 is a 24‑billion‑parameter model based on the llama architecture. It supports instruction following, function calling, and vision reasoning. The model is released under Apache‑2.0 and can be used with vLLM or llama.cpp.

Good at

  • Instruction following
  • Vision reasoning
  • Function calling

Limits

  • Requires ~55 GB GPU RAM in bf16/fp16
  • No native vision API in llama.cpp
  • Large context length 131 072 tokens

Best for

  • Chat assistants needing vision input
  • Tool‑calling workflows
  • Long‑form instruction compliance

Who it’s for. Developers building chat or vision‑enabled assistants who need robust instruction following. The model is suitable for production deployments that can allocate high GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS6.5 GB 8.4 GB
Too big Get file →
IQ2_XS7.2 GB 9.0 GB
Too big Get file →
IQ2_S7.5 GB 9.3 GB
Too big Get file →
IQ2_M8.1 GB 10.0 GB
Too big Get file →
Q2_K8.9 GB 10.7 GB
Too big Get file →
IQ3_XXS9.3 GB 11.1 GB
Too big Get file →
Q2_K_L9.5 GB 11.4 GB
Too big Get file →
IQ3_XS9.9 GB 11.7 GB
Too big Get file →
Q3_K_S10.4 GB 12.2 GB
Too big Get file →
IQ3_M10.7 GB 12.5 GB
Too big Get file →
Q3_K_M11.5 GB 13.3 GB
Too big Get file →
Q3_K_L12.4 GB 14.2 GB
Too big Get file →
IQ4_XS12.8 GB 14.6 GB
Too big Get file →
Q3_K_XL13.0 GB 14.8 GB
Too big Get file →
IQ4_NL13.5 GB 15.3 GB
Too big Get file →
Q4_013.5 GB 15.3 GB
Too big Get file →
Q4_K_S13.5 GB 15.4 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q4_K_L14.8 GB 16.7 GB
Too big Get file →
Q4_114.9 GB 16.7 GB
Too big Get file →
Q5_K_S16.3 GB 18.1 GB
Too big Get file →
Q5_K_M16.8 GB 18.6 GB
Too big Get file →
Q5_K_L17.2 GB 19.0 GB
Too big Get file →
Q6_K19.3 GB 21.2 GB
Too big Get file →
Q6_K_L19.7 GB 21.5 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 IQ2_XXS (6.55 GB file, ~8.4 GB RAM). With 16 GB VRAM IQ4_K_M (14.33 GB file, ~16.2 GB RAM) is a good balance. For 32 GB VRAM consider Q5_K_M (16.76 GB file, ~18.6 GB RAM).

What GPU do you need for Mistral Small 3.2 24B Instruct 2506?

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 IQ3_XS (9.9 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_L (19.7 GB file, about 21.5 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 3.2 24B Instruct 2506 quant should you choose?

Q4_K_M is the usual starting point for Mistral Small 3.2 24B Instruct 2506: 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 IQ2_XXS at 6.5 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 bybartowski
FamilyMistral
Licenseapache-2.0
Downloads (HF)46,332
Last updated2025-12-19

Frequently asked questions about Mistral Small 3.2 24B Instruct 2506

How much VRAM does Mistral Small 3.2 24B Instruct 2506 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 3.2 24B Instruct 2506 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Small 3.2 24B Instruct 2506 GGUF?

It depends on the quant: IQ2_XXS is 6.5 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB, IQ2_M is 8.1 GB, Q2_K is 8.9 GB, IQ3_XXS is 9.3 GB and 21 more.

What context length does Mistral Small 3.2 24B Instruct 2506 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 3.2 24B Instruct 2506 GGUF?

The files are on Hugging Face in the bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-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 3.2 24B Instruct 2506 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 Mistral Small 3.2 on 8 GB VRAM?

Use the IQ2_XXS quant, which requires about 8.4 GB of VRAM at 8 k context.

Does this model support vision in llama.cpp?

Yes, the model includes vision capabilities, but llama.cpp must use the updated chat template for tool calling.

What is the context length of this model?

The model was trained on 131,072 tokens and can handle that context length.

Other GGUFs of Mistral-Small-3.2-24B-Instruct-2506

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other medium models

All medium models →