Qwen2-72B-GGUF / README.md
mradermacher's picture
auto-patch README.md
573cd38 verified
metadata
base_model: Qwen/Qwen2-72B
language:
  - en
library_name: transformers
license: other
license_link: https://huggingface.co/Qwen/Qwen2-72B/blob/main/LICENSE
license_name: tongyi-qianwen
quantized_by: mradermacher
tags:
  - pretrained

About

static quants of https://huggingface.co/Qwen/Qwen2-72B

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2-72B-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 29.9
GGUF IQ3_XS 32.9
GGUF IQ3_S 34.6 beats Q3_K*
GGUF Q3_K_S 34.6
GGUF IQ3_M 35.6
GGUF Q3_K_M 37.8 lower quality
GGUF Q3_K_L 39.6
GGUF IQ4_XS 40.3
GGUF Q4_K_S 44.0 fast, recommended
GGUF Q4_K_M 47.5 fast, recommended
PART 1 PART 2 Q5_K_S 51.5
PART 1 PART 2 Q5_K_M 54.5
PART 1 PART 2 Q6_K 64.4 very good quality
PART 1 PART 2 Q8_0 77.4 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.