Youssofal/Qwen3.8-Flash-Next-MTPLX-Optimized-Speed

Add the MTPLX 2.12.0 prompt speeds against 2.11.3

Recommend 128 GB and up (peak 87 GiB) and point 96 GB Macs to Bare Speed

Model card: library mtplx

Model card: MTPLX 2.11.3 measured speeds, pack quality and search terms

Update README.md

Update README.md

Update README.md

Upload README.md with huggingface_hub

Add files using upload-large-folder tool

Upload vocab.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

metadata: model.safetensors.index.json (weights streaming in background)

metadata: mtplx_runtime.json (weights streaming in background)

metadata: video_preprocessor_config.json (weights streaming in background)

metadata: processor_config.json (weights streaming in background)

metadata: preprocessor_config.json (weights streaming in background)

metadata: merges.txt (weights streaming in background)

metadata: tokenizer_config.json (weights streaming in background)

metadata: chat_template.jinja (weights streaming in background)

metadata: generation_config.json (weights streaming in background)

metadata: config.json (weights streaming in background)

metadata: README-upstream-qwen.md (weights streaming in background)

metadata: LICENSE (weights streaming in background)

metadata: README.md (weights streaming in background)

initial commit