Command A Reasoning 08 2025 needs about 69.8 GB of memory at Q4_K_M (a 67.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.0 GB to 118.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Command A Reasoning 08 2025 – 111 billion‑parameter reasoning model
Command A Reasoning 08 2025 is a 111 billion‑parameter model from CohereLabs. It is optimized for reasoning and tool use. The model is released under a CC‑BY‑NC‑4.0 license and supports a 500 000‑token context window.
Good at
- Reasoning tasks
- Tool integration
- Long‑form content
Limits
- No vision support
- CC‑BY‑NC‑4.0 license
- Large VRAM required for higher‑quality quants
Best for
- Chatbot reasoning
- Automated workflow scripts
- Complex problem solving
Who it’s for. Developers and researchers needing a large reasoning model for non‑commercial projects. The model is suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ1_M | 26.8 GB | 29.5 GB | Too big | Get file → | |
| IQ2_XXS | 30.5 GB | 33.1 GB | Too big | Get file → | |
| IQ2_XS | 33.7 GB | 36.4 GB | Too big | Get file → | |
| IQ2_S | 35.5 GB | 38.1 GB | Too big | Get file → | |
| IQ2_M | 38.4 GB | 41.0 GB | Too big | Get file → | |
| Q2_K | 42.1 GB | 44.8 GB | Too big | Get file → | |
| Q2_K_L | 42.9 GB | 45.5 GB | Too big | Get file → | |
| IQ3_XXS | 43.4 GB | 46.1 GB | Too big | Get file → | |
| IQ3_XS | 46.5 GB | 49.2 GB | Too big | Get file → | |
| Q3_K_S | 49.0 GB | 51.6 GB | Too big | Get file → | |
| IQ3_M | 50.8 GB (2 parts) | 53.5 GB | Too big | Get file → | |
| Q3_K_M | 54.4 GB (2 parts) | 57.1 GB | Too big | Get file → | |
| Q3_K_L | 59.1 GB (2 parts) | 61.8 GB | Too big | Get file → | |
| Q3_K_XL | 59.9 GB (2 parts) | 62.5 GB | Too big | Get file → | |
| IQ4_XS | 60.0 GB (2 parts) | 62.7 GB | Too big | Get file → | |
| IQ4_NL | 63.4 GB (2 parts) | 66.0 GB | Too big | Get file → | |
| Q4_0 | 63.5 GB (2 parts) | 66.2 GB | Too big | Get file → | |
| Q4_K_S | 63.8 GB (2 parts) | 66.4 GB | Too big | Get file → | |
| Q4_K_M | 67.1 GB (2 parts) | 69.8 GB | Too big | Get file → | |
| Q4_K_L | 67.9 GB (2 parts) | 70.5 GB | Too big | Get file → | |
| Q4_1 | 70.0 GB (2 parts) | 72.7 GB | Too big | Get file → | |
| Q5_K_S | 76.8 GB (2 parts) | 79.4 GB | Too big | Get file → | |
| Q5_K_M | 78.8 GB (2 parts) | 81.4 GB | Too big | Get file → | |
| Q6_K | 91.1 GB (3 parts) | 93.8 GB | Too big | Get file → | |
| Q8_0 | 118.0 GB (3 parts) | 120.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (26.83 GB file, 29.5 GB memory). For 16 GB VRAM, Q4_0 (63.52 GB file, 66.2 GB memory) is a good balance. For 24 GB VRAM, Q4_K_M (67.14 GB file, 69.8 GB memory) offers higher quality. Estimates are approximate.
What GPU do you need for Command A Reasoning 08 2025?
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 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_M (26.8 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_XXS (43.4 GB file, about 46.1 GB in use).
Which Command A Reasoning 08 2025 quant should you choose?
Q4_K_M is the usual starting point for Command A Reasoning 08 2025: it balances file size and quality well. Here it is a 67.1 GB file.
The Q8_0 file is 118.0 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 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
Source
Frequently asked questions about Command A Reasoning 08 2025
How much VRAM does Command A Reasoning 08 2025 need?
About 69.8 GB at Q4_K_M with an 8K context window. That is the 67.1 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 Command A Reasoning 08 2025 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Command A Reasoning 08 2025 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_M is 26.8 GB, IQ2_XXS is 30.5 GB, IQ2_XS is 33.7 GB, IQ2_S is 35.5 GB, IQ2_M is 38.4 GB and 20 more.
What context length does Command A Reasoning 08 2025 support?
The GGUF header lists a trained context length of 500,000 tokens (488K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Command A Reasoning 08 2025 GGUF?
The files are on Hugging Face in the bartowski/CohereLabs_command-a-reasoning-08-2025-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 Command A Reasoning 08 2025 use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Command A Reasoning 08 2025 on 8 GB VRAM?
Use the IQ1_M quant, which requires about 29.5 GB of VRAM at 8 k context. 8 GB VRAM is insufficient for any quant of this model.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is licensed under CC‑BY‑NC‑4.0, allowing non‑commercial use with attribution.