Mistral Devstral 2507 CODER Brainstorm20x 34B needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 19 quants, from 0.0 GB to 28.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.9 GB.
Mistral Devstral 2507 CODER Brainstorm20x 34B – a 34B parameter coding model
Mistral Devstral 2507 CODER Brainstorm20x 34B is a 34.1B parameter llama architecture model trained on 131072 context tokens. It supports coding and tool usage and is released under the apache-2.0 license.
Good at
- Large context code generation
- Tool integration
- High‑parameter reasoning
Limits
- Requires large VRAM for full precision
- No vision support
- Context limited to 131072 tokens
Best for
- Complex code synthesis
- Automated tool workflows
- Long‑form documentation generation
Who it’s for. Developers and researchers needing a high‑parameter coding model with extensive context. The model is suitable for environments that can provide sufficient GPU memory and do not require vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.5 GB | Fits | Get file → | |
| IQ2_M | 11.6 GB | 14.1 GB | Too big | Get file → | |
| Q2_K_S | 11.9 GB | 14.4 GB | Too big | Get file → | |
| Q2_K | 12.7 GB | 15.2 GB | Too big | Get file → | |
| IQ3_XXS | 13.3 GB | 15.8 GB | Too big | Get file → | |
| IQ3_XS | 14.2 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_S | 14.9 GB | 17.4 GB | Too big | Get file → | |
| IQ3_S | 15.0 GB | 17.5 GB | Too big | Get file → | |
| IQ3_M | 15.3 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 16.5 GB | 19.0 GB | Too big | Get file → | |
| Q3_K_L | 17.9 GB | 20.4 GB | Too big | Get file → | |
| IQ4_XS | 18.4 GB | 20.9 GB | Too big | Get file → | |
| Q4_0 | 19.5 GB | 21.9 GB | Too big | Get file → | |
| Q4_K_S | 19.5 GB | 22.0 GB | Too big | Get file → | |
| Q4_K_M | 20.7 GB | 23.2 GB | Too big | Get file → | |
| Q4_1 | 21.5 GB | 24.0 GB | Too big | Get file → | |
| Q5_K_S | 23.6 GB | 26.0 GB | Too big | Get file → | |
| Q5_K_M | 24.2 GB | 26.7 GB | Too big | Get file → | |
| Q6_K | 28.0 GB | 30.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 20.68 GB, estimated 23.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (24.23 GB, 26.7 GB memory) is a good balance. For 16 GB VRAM, Q6_K (28.01 GB, 30.5 GB memory) offers the highest quality.
What GPU do you need for Mistral Devstral 2507 CODER Brainstorm20x 34B?
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 2.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (13.3 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (21.5 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.0 GB file, about 30.5 GB in use).
Which Mistral Devstral 2507 CODER Brainstorm20x 34B quant should you choose?
Q4_K_M is the usual starting point for Mistral Devstral 2507 CODER Brainstorm20x 34B: it balances file size and quality well. Here it is a 20.7 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
Frequently asked questions about Mistral Devstral 2507 CODER Brainstorm20x 34B
How much VRAM does Mistral Devstral 2507 CODER Brainstorm20x 34B need?
About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 Devstral 2507 CODER Brainstorm20x 34B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral Devstral 2507 CODER Brainstorm20x 34B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 11.6 GB, Q2_K_S is 11.9 GB, Q2_K is 12.7 GB, IQ3_XXS is 13.3 GB, IQ3_XS is 14.2 GB and 13 more.
What context length does Mistral Devstral 2507 CODER Brainstorm20x 34B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.0 GB at 8K and 7.9 GB at 32K.
Where can I download Mistral Devstral 2507 CODER Brainstorm20x 34B GGUF?
The files are on Hugging Face in the mradermacher/Mistral-Devstral-2507-CODER-Brainstorm20x-34B-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 2507 CODER Brainstorm20x 34B 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?
Use the Q4_K_M quant; it requires about 23.2 GB memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.