Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.
☆216Oct 9, 2026Updated last week
Alternatives and similar repositories for strix-halo-llamacpp
Users that are interested in strix-halo-llamacpp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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.☆257Sep 7, 2026Updated last month
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆20Updated this week
- The Open Source Strix Halo AI engine. Qwen Flash Next Q4_K_XL: 1768.66 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen27B Q4_K_XL: 6…☆789Updated this week
- LLM inference in C/C++☆234Updated this week
- nvitop-style TUI frontend for amdgpu_top (AMDGPU + Strix Halo XDNA NPU)☆96Jul 23, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 5 months ago
- The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)☆1,014Updated this week
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- ☆163Updated this week
- The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)☆131Sep 14, 2026Updated last month
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆160Updated this week
- Mission control for your coding agents. See every session, know which one needs you, and jump straight to it. Your sessions stay in your …☆43Updated this week
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆83Oct 10, 2026Updated last week
- Optimized inference for the DGX Spark and spark clusters☆120Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆90Oct 1, 2026Updated 2 weeks ago
- DESIGN.md guides generated from real website references captured by Fudge.☆116Aug 11, 2026Updated 2 months ago
- This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below☆73Aug 31, 2026Updated last month
- ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, ver…☆56Sep 30, 2026Updated 2 weeks ago
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆166Sep 3, 2026Updated last month
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆84Oct 11, 2026Updated last week
- ☆167Sep 2, 2026Updated last month
- Linux driver for the embedded controller on the Sixunited AXB35-02 board.☆79Aug 20, 2026Updated last month
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆360Oct 3, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Approve and monitor Herdr agents remotely from your phone, a mobile web app for Android/iOS smartphones with push notifications, QR setup…☆298Updated this week
- Local inference with GMKTek evo-x2☆25Nov 3, 2025Updated 11 months ago
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆417Sep 23, 2026Updated 3 weeks ago
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆237Sep 14, 2026Updated last month
- ROCm/AMD GPU benchmark suite for llama.cpp, whisper.cpp, PyTorch☆21Feb 4, 2026Updated 8 months ago
- Verified arithmetic circuit simplifier: Lean 4 proof + Rust FFI☆15Apr 6, 2026Updated 6 months ago
- Air traffic control discipline for agent output. Written for a reader with ADHD.☆124Aug 9, 2026Updated 2 months ago
- collect stats from github and into couchdb☆11May 28, 2016Updated 10 years ago
- Home-enthusiast's guide to fine-tuning 27B+ LLMs on AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — the patches and tuning to make Linux ma…☆30Jun 9, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆11Feb 1, 2023Updated 3 years ago
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆68Updated this week
- C++ inference for Laya typed decisions - supports CUDA, Vulkan, Core ML, CPU☆128Sep 27, 2026Updated 2 weeks ago
- Move Claude Code projects without losing session history — CLI tool to update all path references after renaming or relocating a project …☆25Jul 3, 2026Updated 3 months ago
- Implement V7RC ble control protocol and Wifi real time Vedio Steam on ESP32 CAM☆11Feb 9, 2022Updated 4 years ago
- An erc-20 token with EIP750 style zk private transactions and a new nullifier scheme to allow partial spends☆11Apr 11, 2025Updated last year
- A test docker setup for running Qwen Code on StrixHalo☆18Feb 12, 2026Updated 8 months ago