MI

Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix

MistralGGUF by DavidAUUpdated 2026-04-28
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant8.5 GB
Quick answer

Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix needs about 17.9 GB of memory at Q4_K_M (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.5 GB (IQ2_XXS) to 26.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral Small 3.1 24B Instruct with 128k context and Maxed quantization

Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix is a 23.6B parameter instruction‑tuned model. It supports a 128k token context window and is available in multiple GGUF quantizations. The model is licensed under Apache‑2.0 and can be run locally on a single RTX 4090 or a 32GB RAM MacBook when quantized.

Good at

  • Large context handling
  • Instruction following
  • Creative text generation

Limits

  • No vision components in GGUF
  • Requires 8k context for memory estimates
  • Large memory for high‑precision quants

Best for

  • Local inference for sensitive data
  • Low‑latency function calling
  • Fine‑tuning for domain experts

Who it’s for. Developers and researchers needing a high‑capacity instruction model that can run on consumer GPUs. The model is suitable for local deployment and fine‑tuning on specialized datasets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS8.5 GB 10.4 GB
Too big Get file →
IQ2_XS9.2 GB 11.1 GB
Too big Get file →
IQ3_XXS11.2 GB 13.1 GB
Too big Get file →
IQ3_XS11.8 GB 13.6 GB
Too big Get file →
IQ3_S12.3 GB 14.1 GB
Too big Get file →
IQ3_M12.5 GB 14.3 GB
Too big Get file →
IQ4_XS14.5 GB 16.4 GB
Too big Get file →
IQ4_NL15.2 GB 17.1 GB
Too big Get file →
Q4_K_S15.3 GB 17.1 GB
Too big Get file →
Q4_K_M16.1 GB 17.9 GB
Too big Get file →
Q5_K_S18.0 GB 19.8 GB
Too big Get file →
Q5_K_M18.4 GB 20.3 GB
Too big Get file →
Q6_K20.9 GB 22.8 GB
Too big Get file →
Q8_026.3 GB 28.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XXS or IQ2_XS. For 12‑GB VRAM, IQ3_XXS or IQ3_XS provide a balance of size and performance. If you have 16‑GB VRAM or more, IQ4_XS or Q4_K_S offer higher quality while staying within limits.

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

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 IQ2_XS (9.2 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (12.5 GB file, about 14.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (20.9 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (26.3 GB file, about 28.2 GB in use).

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

Q4_K_M is the usual starting point for Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix: it balances file size and quality well. Here it is a 16.1 GB file.

The Q8_0 file is 26.3 GB, about 1.6 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 8.5 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 byDavidAU
FamilyMistral
Licenseapache-2.0
Downloads (HF)3,803
Last updated2026-04-28

Frequently asked questions about Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix

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

About 17.9 GB at Q4_K_M with an 8K context window. That is the 16.1 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 MAX NEO Imatrix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ2_XXS is 8.5 GB, IQ2_XS is 9.2 GB, IQ3_XXS is 11.2 GB, IQ3_XS is 11.8 GB, IQ3_S is 12.3 GB, IQ3_M is 12.5 GB and 8 more.

What context length does Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix 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 MAX NEO Imatrix GGUF?

The files are on Hugging Face in the DavidAU/Mistral-Small-3.1-24B-Instruct-2503-MAX-NEO-Imatrix-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 MAX NEO Imatrix 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, using the IQ2_XXS or IQ2_XS quant, which estimate 10.4–11.1 GB at 8k context.

Does the model support vision tasks?

The GGUF version does not contain vision components; it is text generation only.

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 DavidAU

All by DavidAU →

More Mistral models

All Mistral →

Other medium models

All medium models →