πŸ“‹ Model Description


base_model: TheDrummer/GLM-Steam-106B-A12B-v1e-FIXED language:
  • en
library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher

About









weighted/imatrix quants of https://huggingface.co/TheDrummer/GLM-Steam-106B-A12B-v1e-FIXED

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

static quants are available at https://huggingface.co/mradermacher/GLM-Steam-106B-A12B-v1e-FIXED-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)

LinkTypeSize/GBNotes
GGUFimatrix0.3imatrix file (for creating your own quants)
GGUFi1-Q2K45.1IQ3XXS probably better
GGUFi1-IQ3_XS49.9
GGUFi1-Q3KS52.5IQ3XS probably better
GGUFi1-IQ3S52.5beats Q3K*
GGUFi1-IQ3_M53.2
GGUFi1-Q3KM57.1IQ3S probably better
GGUFi1-Q3KL59.5IQ3M probably better
GGUFi1-IQ4_XS60.2
GGUFi1-Q4_062.7fast, low quality
GGUFi1-Q4K_S67.0optimal size/speed/quality
GGUFi1-Q4_169.4
GGUFi1-Q4K_M73.0fast, recommended
GGUFi1-Q5K_S78.4
GGUFi1-Q5K_M83.5
GGUFi1-Q6K99.1practically 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.

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-IQ3_M.gguf
LFS Q3
49.43 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-IQ3_S.gguf
LFS Q3
48.79 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-IQ3_XS.gguf
LFS Q3
46.34 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-IQ4_XS.gguf
LFS Q4
55.94 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q2_K.gguf
LFS Q2
41.88 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q3_K_L.gguf
LFS Q3
55.36 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q3_K_M.gguf
LFS Q3
53.12 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q3_K_S.gguf
LFS Q3
48.76 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q4_0.gguf
Recommended LFS Q4
58.29 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q4_1.gguf
LFS Q4
64.5 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q4_K_M.gguf
LFS Q4
67.85 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q4_K_S.gguf
LFS Q4
62.28 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q5_K_M.gguf
LFS Q5
77.68 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q5_K_S.gguf
LFS Q5
72.89 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.i1-Q6_K.gguf
LFS Q6
92.21 GB Download
GLM-Steam-106B-A12B-v1e-FIXED.imatrix.gguf
LFS
217.81 MB Download