About

weighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-110B-Chat

static quants are available at https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-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 23.7 for the desperate
GGUF i1-IQ1_M 26.0 mostly desperate
GGUF i1-IQ2_XXS 29.9
GGUF i1-IQ2_XS 33.1
GGUF i1-IQ2_S 34.4
GGUF i1-IQ2_M 37.5
GGUF i1-Q2_K 41.3 IQ3_XXS probably better
GGUF i1-IQ3_XXS 43.2 lower quality
GGUF i1-IQ3_XS 46.0
GGUF i1-IQ3_S 48.6 beats Q3_K*
GGUF i1-Q3_K_S 48.6 IQ3_XS probably better
GGUF i1-IQ3_M 49.8
PART 1 PART 2 i1-Q3_K_M 53.8 IQ3_S probably better
PART 1 PART 2 i1-Q3_K_L 58.2 IQ3_M probably better
PART 1 PART 2 i1-IQ4_XS 59.7
PART 1 PART 2 i1-Q4_0 63.2 fast, low quality
PART 1 PART 2 i1-Q4_K_S 63.6 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 67.3 fast, recommended
PART 1 PART 2 i1-Q5_K_S 76.7
PART 1 PART 2 i1-Q5_K_M 78.9
PART 1 PART 2 i1-Q6_K 91.3 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. 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.

Downloads last month
24
GGUF
Model size
111B params
Architecture
qwen2

1-bit

2-bit

3-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for mradermacher/Qwen1.5-110B-Chat-i1-GGUF

Quantized
(4)
this model