lthn
/

lemma

Text Generation

4-bit precision

Model card Files Files and versions

4.3 GB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

lthn's picture

Replace bf16 with Q4 MLX — consumer-ready quantisation

585a8a4 verified about 14 hours ago

.gitattributes

1.57 kB
Upload Lemma E4B bf16 (MLX format) — LEK-activated Gemma 4 E4B about 18 hours ago
README.md

197 Bytes
Upload Lemma E4B bf16 (MLX format) — LEK-activated Gemma 4 E4B about 18 hours ago
chat_template.jinja

11.9 kB
Upload Lemma E4B bf16 (MLX format) — LEK-activated Gemma 4 E4B about 18 hours ago
config.json

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

208 Bytes
Upload Lemma E4B bf16 (MLX format) — LEK-activated Gemma 4 E4B about 18 hours ago
model.safetensors

4.27 GB
xet

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

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

32.2 MB
xet

Upload Lemma E4B bf16 (MLX format) — LEK-activated Gemma 4 E4B about 18 hours ago
tokenizer_config.json

2.72 kB
Upload Lemma E4B bf16 (MLX format) — LEK-activated Gemma 4 E4B about 18 hours ago