mradermacher/Qwen2-57B-A14B-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2-57B-A14B

The Qwen2-57B models seem to be broken. I have tried my best, but they likely need to be fixed upstream first. You have been warned.

static quants are available at https://huggingface.co/mradermacher/Qwen2-57B-A14B-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-Q2_K	21.2	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	22.3	lower quality
GGUF	i1-IQ3_XS	23.7
GGUF	i1-Q3_K_S	25.0	IQ3_XS probably better
GGUF	i1-IQ3_S	25.0	beats Q3_K*
GGUF	i1-IQ3_M	25.3
GGUF	i1-Q3_K_M	27.6	IQ3_S probably better
GGUF	i1-Q3_K_L	29.9	IQ3_M probably better
GGUF	i1-IQ4_XS	30.8
GGUF	i1-Q4_0	32.7	fast, low quality
GGUF	i1-Q4_K_S	32.8	optimal size/speed/quality
GGUF	i1-Q4_K_M	35.0	fast, recommended
GGUF	i1-Q5_K_S	39.7
GGUF	i1-Q5_K_M	40.9
GGUF	i1-Q6_K	47.2	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 hardware for calculating the imatrix for these quants.