The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
7 daysStars99624h gain-Score0.0
Find trending repositories by name or description.
The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini PC.