Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
jartine
/
gemma-2-27b-it-llamafile
like
5
Transformers
llamafile
arxiv:
23 papers
License:
other
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
2be5581
gemma-2-27b-it-llamafile
212 GB
1 contributor
History:
11 commits
jartine
Quantize F16 with llamafile-0.8.16
2be5581
verified
about 1 year ago
.gitattributes
2.07 kB
Quantize F16 with llamafile-0.8.16
about 1 year ago
README.md
Safe
29.7 kB
Update README.md
about 1 year ago
gemma-2-27b-it.BF16.cat0.llamafile
50 GB
xet
Quantize BF16 with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.BF16.cat1.llamafile
4.63 GB
xet
Quantize BF16 with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.F16.cat0.llamafile
50 GB
xet
Quantize F16 with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.Q4_K_M.llamafile
16.8 GB
xet
Quantize Q4_K_M with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.Q5_0.llamafile
19.1 GB
xet
Quantize Q5_0 with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.Q5_K_M.llamafile
19.6 GB
xet
Quantize Q5_K_M with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.Q6_K.llamafile
22.5 GB
xet
Quantize Q6_K with llamafile-0.8.16
about 1 year ago
gemma-2-27b-it.Q8_0.llamafile
29.1 GB
xet
Quantize Q8_0 with llamafile-0.8.16
about 1 year ago
gemma-proof.png
Safe
100 kB
Update image
about 1 year ago