MI

Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B

MistralGGUF by mradermacherUpdated 2025-07-30
Download on Hugging Face
Parameters35.8B
Context128K
Layers62
Architecturellama
Smallest quant13.4 GB
Quick answer

Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B needs about 24.2 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 13.4 GB (Q2_K) to 38.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B – 35.8B parameter Llama model

This 35.8B parameter Llama model is trained on 131072 context tokens. It supports coding and reasoning tasks. The model is released under the apache-2.0 license.

Good at

  • Coding
  • Reasoning
  • Large context handling

Limits

  • No vision support
  • Requires high VRAM for larger quants
  • License allows commercial use

Best for

  • Complex code generation
  • Long‑form reasoning
  • Technical documentation

Who it’s for. Developers needing a large language model for code and reasoning tasks. Researchers exploring Llama architecture with extensive context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.4 GB 15.9 GB
Too big Get file →
Q3_K_S15.7 GB 18.2 GB
Too big Get file →
Q3_K_M17.3 GB 19.9 GB
Too big Get file →
Q3_K_L18.8 GB 21.3 GB
Too big Get file →
IQ4_XS19.5 GB 22.0 GB
Too big Get file →
Q4_K_S20.5 GB 23.0 GB
Too big Get file →
Q4_K_M21.7 GB 24.2 GB
Too big Get file →
Q5_K_S24.7 GB 27.3 GB
Too big Get file →
Q5_K_M25.4 GB 28.0 GB
Too big Get file →
Q6_K29.4 GB 32.0 GB
Too big Get file →
Q8_038.0 GB 40.6 GB
Too big Get file →

For 8 GB VRAM use Q2_K (13.35 GB file, 15.9 GB memory). For 16 GB VRAM use Q4_K_M (21.66 GB file, 24.2 GB memory). For 32 GB VRAM use Q6_K (29.38 GB file, 32 GB memory).

What GPU do you need for Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K (13.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_S (20.5 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (38.0 GB file, about 40.6 GB in use).

Which Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B quant should you choose?

Q4_K_M is the usual starting point for Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B: it balances file size and quality well. Here it is a 21.7 GB file.

The Q8_0 file is 38.0 GB, about 1.8 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 at 13.4 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
Parameters35.8B
Layers62
Trained context131,072 tokens
KV cache (fp16)248 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)582
Last updated2025-07-30

Frequently asked questions about Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B

How much VRAM does Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B need?

About 24.2 GB at Q4_K_M with an 8K context window. That is the 21.7 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 Magistral Devstral Instruct FUSED CODER Reasoning 36B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B GGUF?

It depends on the quant: Q2_K is 13.4 GB, Q3_K_S is 15.7 GB, Q3_K_M is 17.3 GB, Q3_K_L is 18.8 GB, IQ4_XS is 19.5 GB, Q4_K_S is 20.5 GB and 5 more.

What context length does Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.3 GB at 32K.

Where can I download Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B GGUF?

The files are on Hugging Face in the mradermacher/Mistral-Magistral-Devstral-Instruct-FUSED-CODER-Reasoning-36B-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 Magistral Devstral Instruct FUSED CODER Reasoning 36B 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, use the Q2_K quant which requires about 15.9 GB of VRAM at 8 k context.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under apache-2.0, allowing commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →