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
quantized
8-bit precision
Instructions to use FrenchCastle/jev-solomon-MLX-8-bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FrenchCastle/jev-solomon-MLX-8-bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download FrenchCastle/jev-solomon-MLX-8-bit --local-dir jev-solomon-MLX-8-bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Ctrl+K
Card: runs at BF16 speed (runtime-bound, 17 s prefill + 2 s per branch), 36 GB memory, MLX cache cap in Quickstart, 4-bit build marked in preparation
c94e0e8 verified