Text Classification
MLX
Safetensors
English
multilingual
apple-silicon
decision-model
system-one
typed-decisions
calibrated-probabilities
structured-output
non-autoregressive
document-understanding
qwen3.8
lora
bf16
Instructions to use FrenchCastle/Solomon-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FrenchCastle/Solomon-MLX-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download FrenchCastle/Solomon-MLX-bf16 --local-dir Solomon-MLX-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
27 days ago
-
Card: measured latency (17 s prefill + 2 s per branch, same at 8-bit), MLX cache cap in Quickstart, 4-bit build marked in preparation
Verified signature6c7ec57 -
model card: full open-source card
Verified signature63ad897 -
Solomon ac4f9ccf on Qwen3.8-27B 1d4bf0f2, BF16 MLX quality profile (55.6 GB, 37 bound files)
Verified signatureb71da11 -
model card: general decision-model framing and tags
Verified signature4020cab -
model card
Verified signatureee02dfe -
initial commit
Verified signature87d66e4