c4ai command r plus GGUF iMat needs about 50.3 GB of memory at IQ3_M (a 47.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 40.7 GB (IQ3_XXS) to 85.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
c4ai command r plus GGUF iMat is a 104B-parameter Command R model in GGUF format, quantized by intervitens-archive. Its trained context length is 128K tokens. The repository has 8 quant files, from 40.7 GB (IQ3_XXS) to 85.2 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 40.7 GB | 43.3 GB | Too big | Get file → | |
| IQ3_XS | 43.6 GB | 46.2 GB | Too big | Get file → | |
| IQ3_S | 46.0 GB | 48.6 GB | Too big | Get file → | |
| IQ3_M | 47.7 GB | 50.3 GB | Too big | Get file → | |
| Q3_K_M | 51.0 GB (2 parts) | 53.6 GB | Too big | Get file → | |
| IQ4_XS | 56.2 GB (2 parts) | 58.8 GB | Too big | Get file → | |
| Q5_K_M | 73.6 GB (2 parts) | 76.3 GB | Too big | Get file → | |
| Q6_K | 85.2 GB (2 parts) | 87.8 GB | Too big | Get file → |
What GPU do you need for c4ai command r plus GGUF iMat?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is IQ3_XS (43.6 GB file, about 46.2 GB in use).
Which c4ai command r plus GGUF iMat quant should you choose?
IQ3_M (47.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ3_XXS at 40.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about c4ai command r plus GGUF iMat
How much VRAM does c4ai command r plus GGUF iMat need?
About 50.3 GB at IQ3_M with an 8K context window. That is the 47.7 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 c4ai command r plus GGUF iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 43.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of c4ai command r plus GGUF iMat GGUF?
It depends on the quant: IQ3_XXS is 40.7 GB, IQ3_XS is 43.6 GB, IQ3_S is 46.0 GB, IQ3_M is 47.7 GB, Q3_K_M is 51.0 GB, IQ4_XS is 56.2 GB and 2 more.
What context length does c4ai command r plus GGUF iMat support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download c4ai command r plus GGUF iMat GGUF?
The files are on Hugging Face in the intervitens-archive/c4ai-command-r-plus-GGUF-iMat repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does c4ai command r plus GGUF iMat 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.