command r needs about 21.6 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 12.8 GB (Q2_K) to 37.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
command r is a 32.3B-parameter Command R model in GGUF format, quantized by cortexso. Its trained context length is 128K tokens. The repository has 20 quant files, from 12.8 GB (Q2_K) to 37.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.8 GB | 14.7 GB | Too big | Get file → | |
| Q2_K | 13.8 GB | 15.7 GB | Too big | Get file → | |
| Q3_K_S | 14.7 GB | 16.6 GB | Too big | Get file → | |
| Q3_K_S | 15.9 GB | 17.7 GB | Too big | Get file → | |
| Q3_K_M | 16.2 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_L | 17.6 GB | 19.4 GB | Too big | Get file → | |
| Q3_K_M | 17.6 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_S | 18.8 GB | 20.7 GB | Too big | Get file → | |
| Q3_K_L | 19.1 GB | 21.0 GB | Too big | Get file → | |
| Q4_K_M | 19.8 GB | 21.6 GB | Too big | Get file → | |
| Q4_K_S | 20.4 GB | 22.2 GB | Too big | Get file → | |
| Q4_K_M | 21.5 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_S | 22.5 GB | 24.3 GB | Too big | Get file → | |
| Q5_K_M | 23.1 GB | 24.9 GB | Too big | Get file → | |
| Q5_K_S | 24.3 GB | 26.2 GB | Too big | Get file → | |
| Q5_K_M | 25.0 GB | 26.9 GB | Too big | Get file → | |
| Q6_K | 26.5 GB | 28.3 GB | Too big | Get file → | |
| Q6_K | 28.7 GB | 30.5 GB | Too big | Get file → | |
| Q8_0 | 34.3 GB | 36.2 GB | Too big | Get file → | |
| Q8_0 | 37.2 GB | 39.0 GB | Too big | Get file → |
What GPU do you need for command r?
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: the best quant that fits is Q2_K (13.8 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.5 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.7 GB file, about 30.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.2 GB file, about 39.0 GB in use).
Which command r quant should you choose?
Q4_K_M is the usual starting point for command r: it balances file size and quality well. Here it is a 19.8 GB file.
The Q8_0 file is 34.3 GB, about 1.7 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 12.8 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 command r
How much VRAM does command r need?
About 21.6 GB at Q4_K_M with an 8K context window. That is the 19.8 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 r on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of command r GGUF?
It depends on the quant: Q2_K is 12.8 GB, Q2_K is 13.8 GB, Q3_K_S is 14.7 GB, Q3_K_S is 15.9 GB, Q3_K_M is 16.2 GB, Q3_K_L is 17.6 GB and 14 more.
What context length does command r 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 command r GGUF?
The files are on Hugging Face in the cortexso/command-r 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 r 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.