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.
☆269Sep 7, 2026Updated 2 months ago
Alternatives and similar repositories for q38rocm
Users that are interested in q38rocm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆227Oct 25, 2026Updated 3 weeks ago
- The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs…☆1,205Updated this week
- Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthrop…☆1,377Updated this week
- qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included☆28Sep 24, 2026Updated last month
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆434Oct 22, 2026Updated 3 weeks 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.
- LLM inference in C/C++☆273Updated this week
- Strixfold: DeepSeek-V4.1-Flash on two AMD Strix Halo boxes over USB4. A HIP backend and Strix Halo kernels for TensorFold.☆76Updated this week
- GPU + XDNA2 NPU inference for AMD Strix Halo (gfx1151): Qwen3.6-35B-A3B, Qwen3.8-27B, Qwen3.8 Flash-Next, Flint and GLM-5.3 Flash (321B M…☆96Nov 12, 2026Updated last week
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆372Nov 9, 2026Updated last week
- llama.cpp fork tuned for Qwen 3.8 Flash-Next on AMD Strix Halo — RDNA3.5 kernel patches, true QSA sparse gather, working MTP, 27 GB engra…☆51Oct 14, 2026Updated last month
- SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)☆42Sep 17, 2026Updated 2 months ago
- ☆2,032Nov 7, 2026Updated last week
- Direct EC fan control for AMD Strix Halo (Ryzen AI Max+ 395) mini-PCs — validated on the Bosgame M5. Fixes sustained-load thermal throttl…☆19Jul 10, 2026Updated 4 months ago
- LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context☆106Updated this week
- 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.
- Halowin Bubo: gufo for native Windows with AMD HIP, tuned for Strix Halo laptops☆28Nov 4, 2026Updated 2 weeks ago
- LLM inference in C/C++☆43Updated this week
- Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a m…☆54Nov 9, 2026Updated last week
- ROCm/AMD GPU benchmark suite for llama.cpp, whisper.cpp, PyTorch☆21Feb 4, 2026Updated 9 months ago
- Fork of gufo-org/gufo with added support for Gemma models (31B and 26B, most quant types) and Deepseek V4.1 Flash (tested with ISTA-DASLa…☆18Nov 11, 2026Updated last week
- A Deepseek V4 Flash 0731 / Vision Exp VLLM stack☆27Sep 24, 2026Updated last month
- Linux driver for the embedded controller on the Sixunited AXB35-02 board.☆87Oct 24, 2026Updated 3 weeks ago
- RDNA-native LLM inference engine in Rust.☆818Updated this week
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆88Nov 4, 2026Updated 2 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Unified terminal monitor for AMD Ryzen AI NPU (XDNA) + iGPU — live utilization for Strix Halo, where amd-smi comes up empty☆41Oct 18, 2026Updated last month
- ☆56Sep 1, 2026Updated 2 months ago
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆60Nov 7, 2026Updated last week
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆87Updated this week
- ☆551Nov 2, 2026Updated 2 weeks ago
- Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, N…☆243Updated this week
- A fast diffusion model engine for image generation and editing.☆40Updated this week
- ☆258Oct 30, 2025Updated last year
- Random AI notes for working with local models or playing around with random machine learning bits.☆64Jun 7, 2026Updated 5 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- NEW ROCmfp4 format for llama.cpp☆158Jun 13, 2026Updated 5 months ago
- Local AI harness for coding agents: detects your GPU and RAM, recommends an engine and model, sizes limits to your context. Any OpenAI-co…☆38Updated this week
- ☆18Nov 4, 2026Updated 2 weeks ago
- NPU-accelerated speech transcription & speaker diarization on AMD Strix Halo: Whisper-v3-turbo on XDNA 2 + pyannote, OpenAI-compatible AP…☆14Aug 31, 2026Updated 2 months ago
- Tensor-parallel DeepSeek V4 Flash inference on dual AMD Strix Halo over OdinLink USB4/TB5 RDMA or Mellanox RoCE v2.☆23Sep 20, 2026Updated last month
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆37Sep 28, 2026Updated last month
- Run Qwen3.8-Flash-Next on one AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). EXL3 4.05 and 3.05 bpw packs, own ROCm/HIP kernels, OpenAI-com…☆33Updated this week
Are these results useful?