qwen38-strix-halo-harness
AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks.
Open the source (opens github.com) https://github.com/aic0d3r/qwen38-strix-halo-harness
What it is
Datasets & benchmarks from aic0d3r.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Get the code
git clone https://github.com/aic0d3r/qwen38-strix-halo-harness.git
Standard git access to a public repository
Setup steps: not provided by the source. Follow the instructions on the source.
Related
-
turnkeyml
Datasets & benchmarksNo-code CLI designed for accelerating ONNX workflows
git clone https://github.com/onnx/turnkeyml.git -
strix-halo-guide
Datasets & benchmarksEvidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
git clone https://github.com/hogeheer499-commits/strix-halo-guide.git -
explicit-edit-benchmark
Datasets & benchmarksBenchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.
git clone https://github.com/alexshpunt/explicit-edit-benchmark.git -
LoopArena
Datasets & benchmarksBenchmarking models as runtime Controllers for Loop Engineering
git clone https://github.com/AMAP-ML/LoopArena.git -
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
OctoCodingBench
Datasets & benchmarksHugging Face dataset by MiniMaxAI
MiniMaxAI/OctoCodingBench