About
weighted/imatrix quants of https://huggingface.co/julien31/Soar-qwen-7b
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Soar-qwen-7b-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 | 2.0 | for the desperate |
| GGUF | i1-IQ1_M | 2.1 | mostly desperate |
| GGUF | i1-IQ2_XXS | 2.4 | |
| GGUF | i1-IQ2_XS | 2.6 | |
| GGUF | i1-IQ2_S | 2.7 | |
| GGUF | i1-IQ2_M | 2.9 | |
| GGUF | i1-Q2_K_S | 2.9 | very low quality |
| GGUF | i1-Q2_K | 3.1 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 3.2 | lower quality |
| GGUF | i1-IQ3_XS | 3.4 | |
| GGUF | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 3.6 | beats Q3_K* |
| GGUF | i1-IQ3_M | 3.7 | |
| GGUF | i1-Q3_K_M | 3.9 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 4.2 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 4.3 | |
| GGUF | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 4.5 | fast, low quality |
| GGUF | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 4.8 | fast, recommended |
| GGUF | i1-Q4_1 | 5.0 | |
| GGUF | i1-Q5_K_S | 5.4 | |
| GGUF | i1-Q5_K_M | 5.5 | |
| GGUF | i1-Q6_K | 6.4 | 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.