mozilla-ai
/

gemma-2-2b-it-llamafile

Model card Files Files and versions

gemma-2-2b-it-llamafile

22.6 GB

1 contributor

History: 10 commits

jartine's picture

Quantize F16 with llamafile-0.8.13

ac9bf08 verified over 1 year ago

.gitattributes

1.98 kB

Quantize F16 with llamafile-0.8.13 over 1 year ago
LICENSE

18.2 kB

Update LICENSE over 1 year ago
README.md

33.1 kB

Update README.md over 1 year ago
gemma-2-2b-it.BF16.llamafile

5.48 GB
xet

Quantize BF16 with llamafile-0.8.13 over 1 year ago
gemma-2-2b-it.F16.llamafile

5.48 GB
xet

Quantize F16 with llamafile-0.8.13 over 1 year ago
gemma-2-2b-it.Q4_K_M.llamafile

1.95 GB
xet

Quantize Q4_K_M with llamafile-0.8.13 over 1 year ago
gemma-2-2b-it.Q5_0.llamafile

2.12 GB
xet

Quantize Q5_0 with llamafile-0.8.13 over 1 year ago
gemma-2-2b-it.Q5_K_M.llamafile

2.16 GB
xet

Quantize Q5_K_M with llamafile-0.8.13 over 1 year ago
gemma-2-2b-it.Q6_K.llamafile

2.39 GB
xet

Quantize Q6_K with llamafile-0.8.13 over 1 year ago
gemma-2-2b-it.Q8_0.llamafile

3.03 GB
xet

Quantize Q8_0 with llamafile-0.8.13 over 1 year ago