lthn
/

lemrd

Image-Text-to-Text

4-bit precision

Model card Files Files and versions

17.3 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

lthn's picture

Replace bf16 with Q4 MLX — consumer-ready quantisation

ac18253 verified about 14 hours ago

.gitattributes

1.57 kB
Upload Lemrd 31B bf16 (MLX format) — LEK-activated Gemma 4 31B about 17 hours ago
README.md

123 Bytes
Update README.md about 17 hours ago
chat_template.jinja

12 kB
Upload Lemrd 31B bf16 (MLX format) — LEK-activated Gemma 4 31B about 17 hours ago
config.json

4.35 kB
Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
generation_config.json

208 Bytes
Upload Lemrd 31B bf16 (MLX format) — LEK-activated Gemma 4 31B about 17 hours ago
model-00001-of-00004.safetensors

5.37 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
model-00002-of-00004.safetensors

5.36 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
model-00003-of-00004.safetensors

5.37 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
model-00004-of-00004.safetensors

1.17 GB
xet

Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
model.safetensors.index.json

167 kB
Replace bf16 with Q4 MLX — consumer-ready quantisation about 14 hours ago
tokenizer.json

32.2 MB
xet

Upload Lemrd 31B bf16 (MLX format) — LEK-activated Gemma 4 31B about 17 hours ago
tokenizer_config.json

2.72 kB
Upload Lemrd 31B bf16 (MLX format) — LEK-activated Gemma 4 31B about 17 hours ago