X (Twitter)

github.com

August 29, 2026

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and a Vulkan backend tuned for AMD Strix Halo. 4.7x on structured output, 1.9x mainline prefill on MoE.

llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and a Vulkan backend tuned for AMD Strix Halo. 4.7x on structured output, 1.9x ma...

github.com

September 14, 2026

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

qwen38-flash-next recipe for solo GB10. Contribute to bilikaz/qwen38-flash-next-recipe development by creating an account on GitHub.

github.com

September 15, 2026

GitHub - peonist-ai/halogen-flash-server: The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151) - peonist-ai/halogen-flash-server

~/bookmarks

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix...

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix...

~/bookmarks

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix...

Discover More

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and a Vulkan backend tuned for AMD Strix Halo. 4.7x on structured output, 1.9x mainline prefill on MoE.

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

GitHub - peonist-ai/halogen-flash-server: The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

Similar Content

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix...

Discover More

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and a Vulkan backend tuned for AMD Strix Halo. 4.7x on structured output, 1.9x mainline prefill on MoE.

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

GitHub - peonist-ai/halogen-flash-server: The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)