Zero-Shot Classification
MLX
Safetensors
qwen3_5
clef
cloudflare
systemone
structured-output
classification
multimodal
custom-code
decision-model
8-bit precision
Instructions to use mlx-community/clef-flash-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/clef-flash-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/clef-flash-8bit --local-dir clef-flash-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
25 days ago
-
clef_mlx.py: use the repo name (not the cache snapshot hash) as the default model name
Verified signaturedfa0993 -
clef_mlx.py: default --model works inside Hub cache snapshots (symlinked files)
Verified signature59f3b98 -
clef_mlx.py: add 'predict' CLI and 'serve' (local POST /v1/systemone server); card: CLI and server docs
Verified signaturee94508b -
Card: zero-shot-classification tag, RAM guide for all variants, limitations, pinned mlx-vlm; clef_mlx: warn on untested mlx-vlm/mlx-lm versions
Verified signatureb5b6a21 -
Add MLX 8-bit conversion of Cloudflare/clef-flash with joint schema head and clef_mlx.py loader
Verified signature8158b14