Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B needs about 28.4 GB of memory at Q4_K_M (a 26.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 16.2 GB (Q2_K) to 46.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B – a large mixture‑of‑experts model
This 43.7B parameter model is a mixture of experts built on the Mistral architecture. It supports coding, reasoning, and tool use. The model was trained on 131072 context tokens and is released under the apache‑2.0 license.
Good at
- Coding tasks
- Complex reasoning
- Tool integration
Limits
- No vision support
- Large VRAM requirement
- Requires 8‑k context for estimates
Best for
- Advanced code generation
- Long‑form reasoning
- Tool‑enabled workflows
Who it’s for. Developers and researchers needing a high‑capacity LLM for coding and reasoning tasks. The model is suitable for environments where large VRAM and CPU resources are available.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 16.2 GB | 18.0 GB | Too big | Get file → | |
| Q3_K_S | 19.1 GB | 20.9 GB | Too big | Get file → | |
| Q3_K_M | 21.1 GB | 22.9 GB | Too big | Get file → | |
| Q3_K_L | 22.8 GB | 24.6 GB | Too big | Get file → | |
| IQ4_XS | 23.7 GB | 25.6 GB | Too big | Get file → | |
| Q4_K_S | 25.0 GB | 26.8 GB | Too big | Get file → | |
| Q4_K_M | 26.5 GB | 28.4 GB | Too big | Get file → | |
| Q5_K_S | 30.1 GB | 32.0 GB | Too big | Get file → | |
| Q5_K_M | 31.1 GB | 32.9 GB | Too big | Get file → | |
| Q6_K | 35.9 GB | 37.7 GB | Too big | Get file → | |
| Q8_0 | 46.4 GB | 48.3 GB | Too big | Get file → |
For 8‑GB VRAM use Q2_K (file size 16.18 GB, estimated 18 GB memory). For 12‑GB VRAM use Q3_K_S (19.05 GB, 20.9 GB). For 16‑GB VRAM use Q4_K_M (26.53 GB, 28.4 GB).
What GPU do you need for Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 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: 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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q3_K_M (21.1 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_S (30.1 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (35.9 GB file, about 37.7 GB in use).
Which Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B quant should you choose?
Q4_K_M is the usual starting point for Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B: it balances file size and quality well. Here it is a 26.5 GB file.
The Q8_0 file is 46.4 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 16.2 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
Source
Frequently asked questions about Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B
How much VRAM does Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B need?
About 28.4 GB at Q4_K_M with an 8K context window. That is the 26.5 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 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B GGUF?
It depends on the quant: Q2_K is 16.2 GB, Q3_K_S is 19.1 GB, Q3_K_M is 21.1 GB, Q3_K_L is 22.8 GB, IQ4_XS is 23.7 GB, Q4_K_S is 25.0 GB and 5 more.
What context length does Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 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 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B GGUF?
The files are on Hugging Face in the mradermacher/Mistral-2x24B-MOE-Power-Devstral-Magistral-Reasoning-Ultimate-44B-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 2x24B MOE Power Devstral Magistral Reasoning Ultimate 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?
Yes, the Q2_K quant requires approximately 18 GB memory at 8‑k context, which fits within 8 GB VRAM when using efficient batching.
Does the model support vision?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.