Mistral 2x22B MOE Power Codestral Ultimate 39B needs about 26.0 GB of memory at Q4_K_M (a 23.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 23 quants, from 8.2 GB (IQ1_S) to 32.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
Mistral 2x22B MOE Power Codestral Ultimate 39B – 39.2B parameter LLM
Mistral 2x22B MOE Power Codestral Ultimate 39B is a 39.2B parameter mixture of experts model based on the llama architecture. It supports a 32768 token context window and is optimized for coding tasks. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Coding assistance
- Mixture of experts efficiency
Limits
- Requires large VRAM for higher quants
- No vision capabilities
- License type is other
Best for
- Code generation
- Large‑scale text analysis
- Research prototyping
Who it’s for. Developers and researchers needing a high‑capacity LLM with extensive context. Suitable for environments where GPU memory can accommodate the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 8.2 GB | 10.6 GB | Too big | Get file → | |
| IQ1_M | 9.0 GB | 11.4 GB | Too big | Get file → | |
| IQ2_XXS | 10.4 GB | 12.8 GB | Too big | Get file → | |
| IQ2_XS | 11.6 GB | 13.9 GB | Too big | Get file → | |
| IQ2_S | 12.0 GB | 14.4 GB | Too big | Get file → | |
| IQ2_M | 13.1 GB | 15.5 GB | Too big | Get file → | |
| Q2_K_S | 13.4 GB | 15.7 GB | Too big | Get file → | |
| Q2_K | 14.4 GB | 16.8 GB | Too big | Get file → | |
| IQ3_XXS | 15.1 GB | 17.5 GB | Too big | Get file → | |
| IQ3_XS | 16.0 GB | 18.4 GB | Too big | Get file → | |
| Q3_K_S | 16.9 GB | 19.3 GB | Too big | Get file → | |
| IQ3_S | 17.0 GB | 19.3 GB | Too big | Get file → | |
| IQ3_M | 17.4 GB | 19.8 GB | Too big | Get file → | |
| Q3_K_M | 18.8 GB | 21.2 GB | Too big | Get file → | |
| Q3_K_L | 20.5 GB | 22.8 GB | Too big | Get file → | |
| IQ4_XS | 20.9 GB | 23.3 GB | Too big | Get file → | |
| Q4_0 | 22.2 GB | 24.6 GB | Too big | Get file → | |
| Q4_K_S | 22.3 GB | 24.6 GB | Too big | Get file → | |
| Q4_K_M | 23.6 GB | 26.0 GB | Too big | Get file → | |
| Q4_1 | 24.5 GB | 26.9 GB | Too big | Get file → | |
| Q5_K_S | 27.0 GB | 29.3 GB | Too big | Get file → | |
| Q5_K_M | 27.7 GB | 30.1 GB | Too big | Get file → | |
| Q6_K | 32.1 GB | 34.5 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (file size 8.23 GB, estimated 10.6 GB memory). For 12 GB VRAM use IQ2_XS (11.56 GB, 13.9 GB memory). For 16 GB VRAM use Q2_K (14.4 GB, 16.8 GB memory). Estimates are approximate.
What GPU do you need for Mistral 2x22B MOE Power Codestral Ultimate 39B?
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 IQ1_M (9.0 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K_S (13.4 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (20.9 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (27.7 GB file, about 30.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (32.1 GB file, about 34.5 GB in use).
Which Mistral 2x22B MOE Power Codestral Ultimate 39B quant should you choose?
Q4_K_M is the usual starting point for Mistral 2x22B MOE Power Codestral Ultimate 39B: it balances file size and quality well. Here it is a 23.6 GB file.
If memory is tight, the smallest file is IQ1_S at 8.2 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
Frequently asked questions about Mistral 2x22B MOE Power Codestral Ultimate 39B
How much VRAM does Mistral 2x22B MOE Power Codestral Ultimate 39B need?
About 26.0 GB at Q4_K_M with an 8K context window. That is the 23.6 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 2x22B MOE Power Codestral Ultimate 39B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral 2x22B MOE Power Codestral Ultimate 39B GGUF?
It depends on the quant: IQ1_S is 8.2 GB, IQ1_M is 9.0 GB, IQ2_XXS is 10.4 GB, IQ2_XS is 11.6 GB, IQ2_S is 12.0 GB, IQ2_M is 13.1 GB and 17 more.
What context length does Mistral 2x22B MOE Power Codestral Ultimate 39B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download Mistral 2x22B MOE Power Codestral Ultimate 39B GGUF?
The files are on Hugging Face in the mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-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 2x22B MOE Power Codestral Ultimate 39B use?
Hugging Face lists the license as other. 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 IQ1_S quantization which requires about 10.6 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
The model supports a 32768 token context window.