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

Model card: list as image-text-to-text, since the pack ships the vision tower

MTPLX 2.12.0 is out: the card no longer calls it the next release

Model card in the MTPLX card format, matching Optimized Speed

Declare the Qwen 3.8 sampler (temperature 1.0, top-p 0.95, top-k 20) in mtplx_runtime.json, as the other Flash-Next packs do

Plain card for the 2.12.0 release under the mtplx library: memory, speed status and the tensor table

Describe the streaming audit in a valid explicitly unverified runtime contract

Publish the 8-bit Flash-Next Quality pack for upcoming MTPLX 2.12.0

initial commit