MI

Mistral Small 24B Instruct 2501 Heretic

MistralGGUF by mradermacherUpdated 2026-02-17
Download on Hugging Face
Parameters23.6B
Context32K
Layers40
Architecturellama
Smallest quant0.0 GB
Quick answer

Mistral Small 24B Instruct 2501 Heretic 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 24 quants, from 0.0 GB to 19.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral Small 24B Instruct 2501 Heretic – 23.6B parameter Llama model

Mistral Small 24B Instruct 2501 Heretic is a 23.6B parameter Llama model trained on 32768 token context. It is released under the Apache-2.0 license and is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Large context handling
  • LLM inference with GGUF

Limits

  • Large memory requirement for higher quants
  • Requires 8k context for memory estimates

Best for

  • Chatbot instruction tasks
  • Text generation with long context
  • Fine‑tuning on custom prompts

Who it’s for. Developers needing a 24B instruction model with an open license. Suitable for local inference with GGUF.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.9 GB
Fits Get file →
IQ1_S5.3 GB 7.1 GB
Fits Get file →
IQ1_M5.8 GB 7.6 GB
Tight Get file →
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_K_S8.3 GB 10.2 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 →
IQ3_XS9.9 GB 11.7 GB
Too big Get file →
Q3_K_S10.4 GB 12.2 GB
Too big Get file →
IQ3_S10.4 GB 12.3 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 →
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_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 →
Q6_K19.3 GB 21.2 GB
Too big Get file →

For 8GB VRAM, use IQ1_S (5.27GB file, 7.1GB memory at 8k context). For 12GB VRAM, use Q3_K_S (10.4GB file, 12.2GB memory). For 16GB VRAM, use Q4_K_M (14.33GB file, 16.2GB memory).

What GPU do you need for Mistral Small 24B Instruct 2501 Heretic?

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: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_M (5.8 GB file, about 7.6 GB in use).
  • 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 (19.3 GB file, about 21.2 GB in use).

Which Mistral Small 24B Instruct 2501 Heretic quant should you choose?

Q4_K_M is the usual starting point for Mistral Small 24B Instruct 2501 Heretic: it balances file size and quality well. Here it is a 14.3 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,896
Last updated2026-02-17

Frequently asked questions about Mistral Small 24B Instruct 2501 Heretic

How much VRAM does Mistral Small 24B Instruct 2501 Heretic 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 24B Instruct 2501 Heretic on an 8 GB GPU?

Yes, with IQ1_M: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mistral Small 24B Instruct 2501 Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 5.3 GB, IQ1_M is 5.8 GB, IQ2_XXS is 6.5 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB and 18 more.

What context length does Mistral Small 24B Instruct 2501 Heretic support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 24B Instruct 2501 Heretic GGUF?

The files are on Hugging Face in the mradermacher/Mistral-Small-24B-Instruct-2501-Heretic-i1-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 24B Instruct 2501 Heretic 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 8GB VRAM?

The smallest quant IQ1_S uses 5.27GB file and requires about 7.1GB memory at 8k context, so 8GB VRAM is borderline.

What license does it use?

Apache-2.0.

Which quant gives better quality?

IQ quants are often preferable over similar sized non-IQ quants.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other medium models

All medium models →