base_model: roslein/c4ai-command-a-03-2025-abliterated
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
About
weighted/imatrix quants of https://huggingface.co/roslein/c4ai-command-a-03-2025-abliterated
static quants are available at https://huggingface.co/mradermacher/c4ai-command-a-03-2025-abliterated-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 | i1-IQ1_S | 24.7 | for the desperate |
| GGUF | i1-IQ1_M | 26.9 | mostly desperate |
| GGUF | i1-IQ2_XXS | 30.6 | |
| GGUF | i1-IQ2_XS | 33.8 | |
| GGUF | i1-IQ2_S | 35.6 | |
| GGUF | i1-IQ2_M | 38.5 | |
| GGUF | i1-Q2_K_S | 39.1 | very low quality |
| GGUF | i1-Q2_K | 42.2 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 43.5 | lower quality |
| GGUF | i1-IQ3_XS | 46.6 | |
| GGUF | i1-Q3_K_S | 49.1 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 49.2 | beats Q3_K* |
| PART 1 PART 2 | i1-IQ3_M | 50.9 | |
| PART 1 PART 2 | i1-Q3_K_M | 54.5 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 59.2 | IQ3_M probably better |
| PART 1 PART 2 | i1-IQ4_XS | 60.1 | |
| PART 1 PART 2 | i1-Q4_0 | 63.6 | fast, low quality |
| PART 1 PART 2 | i1-Q4_K_S | 63.9 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 67.2 | fast, recommended |
| PART 1 PART 2 | i1-Q4_1 | 70.1 | |
| PART 1 PART 2 | i1-Q5_K_S | 76.9 | |
| PART 1 PART 2 | i1-Q5_K_M | 78.9 | |
| PART 1 PART 2 | i1-Q6_K | 91.2 | practically like static Q6_K |
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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.