hogeheer499-commits/strix-halo-guide

Open Issues Need Help

Collect benchmark reports from more Strix Halo systems about 2 hours ago

help wanted reproducibility benchmark

278

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.

Python

#amd#beelink#benchmark#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc#ollama#radeon-8060s#rocm#ryzen-ai-halo#ryzen-ai-max#ryzen-ai-max-395#strix-halo#unified-memory#vulkan

Measure same-machine Windows vs Linux local LLM performance 3 months ago

help wanted reproducibility benchmark

hogeheer499-commits/strix-halo-guide

278

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.

Python

#amd#beelink#benchmark#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc#ollama#radeon-8060s#rocm#ryzen-ai-halo#ryzen-ai-max#ryzen-ai-max-395#strix-halo#unified-memory#vulkan

Validate tokens-per-watt with reliable power telemetry 3 months ago

help wanted reproducibility benchmark

hogeheer499-commits/strix-halo-guide

278

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.

Python

#amd#beelink#benchmark#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc#ollama#radeon-8060s#rocm#ryzen-ai-halo#ryzen-ai-max#ryzen-ai-max-395#strix-halo#unified-memory#vulkan

Reproduce vLLM throughput on a comparable Strix Halo workload 3 months ago

help wanted model-request benchmark

hogeheer499-commits/strix-halo-guide

278

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.

Python

#amd#beelink#benchmark#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc#ollama#radeon-8060s#rocm#ryzen-ai-halo#ryzen-ai-max#ryzen-ai-max-395#strix-halo#unified-memory#vulkan

Community benchmark request: llama.cpp RPC over USB4 Ethernet 3 months ago

help wanted reproducibility benchmark

hogeheer499-commits/strix-halo-guide

278

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.

Python

#amd#beelink#benchmark#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc#ollama#radeon-8060s#rocm#ryzen-ai-halo#ryzen-ai-max#ryzen-ai-max-395#strix-halo#unified-memory#vulkan

Add a community results table once benchmark reports arrive 3 months ago

documentation help wanted good first issue

hogeheer499-commits/strix-halo-guide

278

Strix Halo guide for AMD Ryzen AI MAX+ 395 / Radeon 8060S local LLM setup and benchmarks: Ollama, llama.cpp, Vulkan/RADV, ROCm, GGUF, and raw evidence.

Python

#amd#beelink#benchmark#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc#ollama#radeon-8060s#rocm#ryzen-ai-halo#ryzen-ai-max#ryzen-ai-max-395#strix-halo#unified-memory#vulkan