MI

Mistral Devstral 2505 CODER Brainstorm40x 44B

MistralGGUF by mradermacherUpdated 2025-12-18
Download on Hugging Face
Parameters43.6B
Context128K
Layers76
Architecturellama
Smallest quant0.0 GB
Quick answer

Mistral Devstral 2505 CODER Brainstorm40x 44B needs about 29.4 GB of memory at Q4_K_M (a 26.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.0 GB to 35.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.2 GB.

Mistral Devstral 2505 CODER Brainstorm40x 44B – a 43.6B parameter coding model

This model is a 43.6B parameter llama architecture trained on 131072 tokens. It is optimized for coding tasks and available in multiple GGUF quantizations. The model is released under the apache-2.0 license.

Good at

  • Coding assistance
  • Code generation
  • Programming queries

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • No mixture of experts

Best for

  • Developers writing code
  • Automated code review
  • Learning programming concepts

Who it’s for. Engineers and developers who need a large language model focused on coding. The model is suitable for integration into IDEs, code completion tools, or educational platforms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.1 GB
Fits Get file →
IQ1_S9.4 GB 12.4 GB
Too big Get file →
IQ1_M10.3 GB 13.3 GB
Too big Get file →
IQ2_XXS11.8 GB 14.9 GB
Too big Get file →
IQ2_XS13.1 GB 16.1 GB
Too big Get file →
IQ2_S13.5 GB 16.6 GB
Too big Get file →
IQ2_M14.7 GB 17.8 GB
Too big Get file →
Q2_K_S15.1 GB 18.1 GB
Too big Get file →
Q2_K16.2 GB 19.2 GB
Too big Get file →
IQ3_XXS17.0 GB 20.0 GB
Too big Get file →
IQ3_XS18.1 GB 21.1 GB
Too big Get file →
Q3_K_S19.0 GB 22.0 GB
Too big Get file →
IQ3_S19.1 GB 22.1 GB
Too big Get file →
IQ3_M19.5 GB 22.5 GB
Too big Get file →
Q3_K_M21.0 GB 24.1 GB
Too big Get file →
Q3_K_L22.8 GB 25.8 GB
Too big Get file →
IQ4_XS23.4 GB 26.5 GB
Too big Get file →
Q4_024.8 GB 27.8 GB
Too big Get file →
Q4_K_S24.9 GB 27.9 GB
Too big Get file →
Q4_K_M26.4 GB 29.4 GB
Too big Get file →
Q4_127.4 GB 30.4 GB
Too big Get file →
Q5_K_S30.1 GB 33.1 GB
Too big Get file →
Q5_K_M30.9 GB 34.0 GB
Too big Get file →
Q6_K35.8 GB 38.8 GB
Too big Get file →

For 8‑GB VRAM, the smallest quant is IQ1_S at 12.4 GB, which exceeds the limit. A 16‑GB VRAM setup can run Q2_K_S (18.1 GB) or Q2_K (19.2 GB). With 24‑GB VRAM, Q4_K_M (29.4 GB) or Q5_K_S (33.1 GB) are viable options. Estimates are approximate.

What GPU do you need for Mistral Devstral 2505 CODER Brainstorm40x 44B?

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 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.1 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.1 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.1 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_XXS (11.8 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_M (19.5 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_1 (27.4 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (35.8 GB file, about 38.8 GB in use).

Which Mistral Devstral 2505 CODER Brainstorm40x 44B quant should you choose?

Q4_K_M is the usual starting point for Mistral Devstral 2505 CODER Brainstorm40x 44B: it balances file size and quality well. Here it is a 26.4 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
Parameters43.6B
Layers76
Trained context131,072 tokens
KV cache (fp16)304 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,496
Last updated2025-12-18

Frequently asked questions about Mistral Devstral 2505 CODER Brainstorm40x 44B

How much VRAM does Mistral Devstral 2505 CODER Brainstorm40x 44B need?

About 29.4 GB at Q4_K_M with an 8K context window. That is the 26.4 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 Devstral 2505 CODER Brainstorm40x 44B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mistral Devstral 2505 CODER Brainstorm40x 44B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 9.4 GB, IQ1_M is 10.3 GB, IQ2_XXS is 11.8 GB, IQ2_XS is 13.1 GB, IQ2_S is 13.5 GB and 18 more.

What context length does Mistral Devstral 2505 CODER Brainstorm40x 44B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.2 GB at 32K.

Where can I download Mistral Devstral 2505 CODER Brainstorm40x 44B GGUF?

The files are on Hugging Face in the mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-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 Devstral 2505 CODER Brainstorm40x 44B 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?

The smallest available quant requires 12.4 GB of VRAM, so 8 GB is insufficient.

What is the maximum context length?

The model was trained on 131072 tokens and supports up to that context length.

Under what license is this model released?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →