philipjohnbasile/DeepSeek-V4-Flash-0731-MLX-M5Max-TargetOnly
21.3k
Clarify release scope and connect the model portfolio
Add a practical start guide with runtime, memory, attribution, and evidence scope
Document GPQA Diamond benchmark and oMLX support
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Document experimental MTPLX support and performance limits
Document original-model comparison
Upload validated target-only MLX weights and tokenizer
Add upstream MIT license
Add experimental model card and verified M5 Max smoke
initial commit