RolanDorisTech
/

Qwen3.8-9B-Distill-MLX-4bit

4-bit precision

Model card Files Files and versions

Qwen3.8-9B-Distill-MLX-4bit

5.3 GB

Ctrl+K

Ctrl+K

1 contributor

History: 30 commits

RolanDorisTech's picture

fix top link line break with br

a6a9bd7 verified 29 days ago

.gitattributes

1.69 kB
V14 final charts - title first, line under 30 days ago
9b_accuracy.png

126 kB
xet

V14 final charts - y-label axis starts at 60 30 days ago
9b_accuracy_dark.png

58.9 kB
Add dark 9B accuracy chart about 1 month ago
9b_accuracy_delta_vs_bf16.png

131 kB
xet

V14 final charts - title first, line under 30 days ago
README.md

11 kB
fix top link line break with br 29 days ago
benchmark_results.json

50.9 kB
Update benchmark_results.json to current IDs about 1 month ago
chat_template.jinja

7.76 kB
Upload 9B-oQ4e LFS fixed - DISABLE_XET about 1 month ago
config.json

33.9 kB
Upload 9B-oQ4e LFS fixed - DISABLE_XET about 1 month ago
generation_config.json

164 Bytes
Upload 9B-oQ4e LFS fixed - DISABLE_XET about 1 month ago
model.safetensors

5.28 GB
xet

Fix 9B-4bit: rename PLACEHOLDER -> model.safetensors (4.9GB single file, like 2B/4B) about 1 month ago
oq_imatrix_report.json

16.9 kB
Upload 9B-oQ4e LFS fixed - DISABLE_XET about 1 month ago
tokenizer.json

20 MB
xet

Upload 9B-oQ4e LFS fixed - DISABLE_XET about 1 month ago
tokenizer_config.json

1.16 kB
Upload 9B-oQ4e LFS fixed - DISABLE_XET about 1 month ago