The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
☆1,014Oct 17, 2026Updated this week
Alternatives and similar repositories for halogen-flash-server
Users that are interested in halogen-flash-server are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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
- ☆163Updated this week
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆216Oct 9, 2026Updated last week
- Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini P…☆182Updated this week
- 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
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)☆131Sep 14, 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
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆417Sep 23, 2026Updated 3 weeks ago
- ☆1,998Updated this week
- LLM inference in C/C++☆234Updated this week
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆68Updated this week
- ☆90Oct 1, 2026Updated 2 weeks ago
- ☆257Oct 30, 2025Updated 11 months ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆26,707Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Convert and Run Exl3 format LLM quant on Apple Silicon.☆58Aug 24, 2026Updated last month
- Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, s…☆999Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,056Updated this week
- This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below☆73Aug 31, 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
- ☆536Oct 4, 2026Updated 2 weeks ago
- Local inference with GMKTek evo-x2☆25Nov 3, 2025Updated 11 months ago
- ☆63Oct 3, 2026Updated 2 weeks ago
- Strata minus the bullshit. clone, rsync to prod, compile and go☆112Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆81Updated this week
- Code for free in claude-code, hermes, codex, vscode, .. and more☆69Sep 22, 2026Updated 3 weeks ago
- Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the laye…☆93Updated this week
- Random AI notes for working with local models or playing around with random machine learning bits.☆64Jun 7, 2026Updated 4 months ago
- LLM inference in C/C++☆64Updated this week
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆263Oct 11, 2026Updated last week
- Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration☆782Updated this week
- This repository builds llama.cpp for Strix Halo devices.☆68Updated this week
- Palm on-device acceleration capabilities.☆81Updated this week
- 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.
- FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.☆14,555Updated this week
- LLM Inference Engine for Metal and CUDA.☆1,359Updated this week
- Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE☆151Updated this week
- Make any agent harness multimodal-native.☆3,141Oct 11, 2026Updated last week
- llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 95+ tok/s over a 100K-token gen…☆178Updated this week
- Linux driver for the embedded controller on the Sixunited AXB35-02 board.☆79Aug 20, 2026Updated last month
- Hierarchical, steerable subagent threads for pi☆111Updated this week