Qwen2-57B-A14B-GGUF / README.md
mradermacher's picture
Update README.md
33e5077 verified
metadata
base_model: Qwen/Qwen2-57B-A14B
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - pretrained
  - moe

About

static 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.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2-57B-A14B-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 21.2
GGUF IQ3_XS 23.7
GGUF Q3_K_S 25.0
GGUF IQ3_S 25.0 beats Q3_K*
GGUF IQ3_M 25.3
GGUF Q3_K_M 27.6 lower quality
GGUF Q3_K_L 29.9
GGUF IQ4_XS 31.1
GGUF Q4_K_S 32.8 fast, recommended
GGUF Q4_K_M 35.0 fast, recommended
GGUF Q5_K_S 39.7
GGUF Q5_K_M 40.9
GGUF Q6_K 47.2 very good quality
PART 1 PART 2 Q8_0 61.1 fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

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.