mradermacher/GLM-4.7-Flash-49B-i1-GGUF

---

base_model: win10/GLM-4.7-Flash-49B language:

• en

library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/win10/GLM-4.7-Flash-49B

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/GLM-4.7-Flash-49B-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	imatrix	0.2	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	9.9	for the desperate
GGUF	i1-IQ1_M	10.9	mostly desperate
GGUF	i1-IQ2_XXS	12.7
GGUF	i1-IQ2_XS	14.2
GGUF	i1-IQ2_S	14.4
GGUF	i1-IQ2_M	15.8
GGUF	i1-Q2K_S	16.4	very low quality
GGUF	i1-Q2K	17.6	IQ3XXS probably better
GGUF	i1-IQ3_XXS	18.6	lower quality
GGUF	i1-IQ3_XS	19.7
GGUF	i1-IQ3S	20.8	beats Q3K*
GGUF	i1-Q3KS	20.8	IQ3XS probably better
GGUF	i1-IQ3_M	21.1
GGUF	i1-Q3KM	23.0	IQ3S probably better
GGUF	i1-Q3KL	24.9	IQ3M probably better
GGUF	i1-IQ4_XS	25.6
GGUF	i1-Q4_0	27.2	fast, low quality
GGUF	i1-Q4K_S	27.3	optimal size/speed/quality
GGUF	i1-Q4K_M	29.0	fast, recommended
GGUF	i1-Q4_1	30.0
GGUF	i1-Q5K_S	33.0
GGUF	i1-Q5K_M	34.0
GGUF	i1-Q6K	39.3	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. 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.