Welcome! Type "help" for available commands.

$

Loading terminal interface...

Experience Education

Projects Bookmarks Investments Contact Blog

Welcome! Type "help" for available commands.

$

Loading terminal interface...

AMD Strix Halo Bookmarks | William Callahan - Bookmarks

~/bookmarks

Similar Content

A collection of bookmarks filtered by the tag "AMD Strix Halo".

Filter by:

Showing 1-11 of 11 bookmarks tagged with "AMD Strix Halo"

All Stories

GitHub - gufo-org/gufo: Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,628.52pp, 59.41tg single user, 157.22 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2

GitHub - gufo-org/gufo: Strix Halo inference engine. Qwen Flash Next...

On-Device AI AMD Strix Halo Local LLM Inference

Oct 2, 2026

GitHub - claudejaune/Qwen3.8-Halogen-Flash-Strix-Halo: Run Qwen3.8-Flash-Next (180B, 6B active) on a single AMD Strix Halo via the halogen-flash-server container

GitHub - claudejaune/Qwen3.8-Halogen-Flash-Strix-Halo: Run Qwen3.8-Flash-Next (180B, 6B active) on a...

Mixture-of-Experts Halogen Flash Server Qwen 3.8 Flash

Oct 2, 2026

GitHub - julianmb/halofpx: High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), bleeding-edge RDNA 3.5 Wave64/ROCmFP4 kernels, and silicon-tuned profiles.

GitHub - julianmb/halofpx: High-performance Lemonade alternative for AMD Strix Halo...

AMD Strix Halo RDNA 3.5 Local LLM Inference

Oct 1, 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.

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and...

LLM Inference Vulkan Speculative Decoding

Aug 29, 2026

AMD Strix Halo — Backend Benchmarks (Grid View)

kyuz0.github.io

AMD Strix Halo — Backend Benchmarks (Grid View)

LLM Inference Vulkan Model Quantization

Aug 26, 2026

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.

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

Speculative Decoding AMD Strix Halo ROCmFP4

Aug 19, 2026

vmlinux/Muse-Glimmer-30B-ROCmFPX-GGUF · Hugging Face

vmlinux/Muse-Glimmer-30B-ROCmFPX-GGUF · Hugging Face

Model Quantization ROCmFPX AMD Strix Halo

Aug 11, 2026

amd-strix-halo-vllm-toolboxes/rdma_cluster/setup_guide.md at main · kyuz0/amd-strix-halo-vllm-toolboxes

amd-strix-halo-vllm-toolboxes/rdma_cluster/setup_guide.md at main · kyuz0/amd-strix-halo-vllm-toolboxes

Tensor Parallelism RDMA Distributed Inference

Jun 28, 2026

Running 122B-Parameter LLMs Locally on AMD Strix Halo for OpenClaw: A Deep Dive | LinkedIn

Running 122B-Parameter LLMs Locally on AMD Strix Halo for OpenClaw:...

LLM Inference Local LLMs AMD Strix Halo

Mar 21, 2026

GLM 4.5-Air-106B and Qwen3-235B on AMD “Strix Halo” AI Ryzen MAX+ 395 (HP Z2 G1a Mini Workstation)

GLM 4.5-Air-106B and Qwen3-235B on AMD “Strix Halo” AI Ryzen...

Ryzen AI PCs Large Language Models Benchmarks

Sep 24, 2025

GitHub - kyuz0/amd-strix-halo-toolboxes

GitHub - kyuz0/amd-strix-halo-toolboxes

Developer Toolboxes Large Language Models GPU Acceleration

Sep 24, 2025

Discover More

github.com

August 11, 2026

GitHub - kyuz0/strix-halo-ds4-toolbox

GitHub - kyuz0/strix-halo-ds4-toolbox

Contribute to kyuz0/strix-halo-ds4-toolbox development by creating an account on GitHub.

GGUF Models DeepSeek V4 Local LLM Inference Strix Halo ROCm

LINK