mradermacher/Qwen1.5-72B-i1-GGUF

---

base_model: Qwen/Qwen1.5-72B language:

• en

library_name: transformers license: other license_link: https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE license_name: tongyi-qianwen quantized_by: mradermacher tags:

• pretrained

---

About

weighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-72B

static quants are available at https://huggingface.co/mradermacher/Qwen1.5-72B-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	16.3	for the desperate
GGUF	i1-IQ1_M	17.7	mostly desperate
GGUF	i1-IQ2_XXS	19.9
GGUF	i1-IQ2_XS	21.8
GGUF	i1-IQ2_S	23.5
GGUF	i1-IQ2_M	25.3
GGUF	i1-IQ3_XXS	27.8	lower quality
GGUF	i1-Q2K	28.6	IQ3XXS probably better
GGUF	i1-IQ3_XS	30.0
GGUF	i1-IQ3S	31.7	beats Q3K*
GGUF	i1-Q3KS	33.0	IQ3XS probably better
GGUF	i1-IQ3_M	34.0
GGUF	i1-Q3KM	36.0	IQ3S probably better
GGUF	i1-Q3KL	38.6	IQ3M probably better
GGUF	i1-IQ4_XS	38.9
GGUF	i1-Q4_0	41.2	fast, low quality
GGUF	i1-Q4K_S	42.0	optimal size/speed/quality
GGUF	i1-Q4K_M	44.2	fast, recommended
GGUF	i1-Q5K_S	50.0
PART 1 PART 2	i1-Q5KM	51.4
PART 1 PART 2	i1-Q6K	59.4	practically like static Q6K

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.