About
static quants of https://huggingface.co/CohereForAI/c4ai-command-r-plus
You should use --override-kv tokenizer.ggml.pre=str:command-r and a current llama.cpp version to work around a bug in llama.cpp that made these quants.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/c4ai-command-r-plus-i1-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q2_K | 39.6 | |
| GGUF | IQ3_XS | 43.7 | |
| GGUF | Q3_K_S | 46.0 | |
| GGUF | IQ3_S | 46.1 | beats Q3_K* |
| GGUF | IQ3_M | 47.8 | |
| PART 1 PART 2 | Q3_K_M | 51.1 | lower quality |
| PART 1 PART 2 | Q3_K_L | 55.5 | |
| PART 1 PART 2 | IQ4_XS | 56.8 | |
| PART 1 PART 2 | Q4_K_S | 59.7 | fast, recommended |
| PART 1 PART 2 | Q4_K_M | 62.9 | fast, recommended |
| PART 1 PART 2 | Q5_K_S | 71.9 | |
| PART 1 PART 2 | Q5_K_M | 73.7 | |
| PART 1 PART 2 | Q6_K | 85.3 | very good quality |
| PART 1 PART 2 PART 3 | Q8_0 | 110.4 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.
- Downloads last month
- 288