Qwen1.5-32B-i1-GGUF / README.md
mradermacher's picture
auto-patch README.md
182bb14 verified
metadata
base_model: Qwen/Qwen1.5-32B
language:
  - en
library_name: transformers
license: other
license_link: https://huggingface.co/Qwen/Qwen1.5-32B/blob/main/LICENSE
license_name: tongyi-qianwen-research
quantized_by: mradermacher
tags:
  - pretrained

About

weighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-32B

static quants are available at https://huggingface.co/mradermacher/Qwen1.5-32B-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 7.3 for the desperate
GGUF i1-IQ1_M 8.0 mostly desperate
GGUF i1-IQ2_XXS 9.1
GGUF i1-IQ2_XS 10.0
GGUF i1-IQ2_S 10.4
GGUF i1-IQ2_M 11.3
GGUF i1-Q2_K 12.3 IQ3_XXS probably better
GGUF i1-IQ3_XXS 12.8 lower quality
GGUF i1-IQ3_XS 13.7
GGUF i1-Q3_K_S 14.4 IQ3_XS probably better
GGUF i1-IQ3_S 14.4 beats Q3_K*
GGUF i1-IQ3_M 14.8
GGUF i1-Q3_K_M 15.9 IQ3_S probably better
GGUF i1-Q3_K_L 17.2 IQ3_M probably better
GGUF i1-IQ4_XS 17.7
GGUF i1-Q4_0 18.7 fast, low quality
GGUF i1-Q4_K_S 18.7 optimal size/speed/quality
GGUF i1-Q4_K_M 19.8 fast, recommended
GGUF i1-Q5_K_S 22.6
GGUF i1-Q5_K_M 23.2
GGUF i1-Q6_K 26.8 practically like static Q6_K

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.