Halogen

Halogen 0.20.0 is out for Strix Halo • OvisOCR3 document parsing on the @AIatAMD NPU (your own weights) • OCRBench 85.7 vs 85.3 upstream • ROCm 10.1: ~9–15% less energy, same speed • 2–6% faster prompt reading on Qwen3.8-Flash-Next github.com/peonist-ai/haloge…

Halogen 0.19.1 for Strix Halo: • XRT now in the image: NPU needs only the host driver and firmware • Malformed tool schemas get a 400 instead of locking up generation slots • Faster first token when a /v1/completions prompt extends a recent one github.com/peonist-ai/haloge…

Halogen 0.19.0 for @AIatAMD Strix Halo: • Preview: Halogen Spotter, an opt-in NPU agent guard that checks tool results • Whole-file rewrites by coding agents ~30% faster • NPU stability fixes Spotter: peonist.ai/halogen/docs/agen… Changelog: github.com/peonist-ai/haloge…

Halogen Flash is now a backend in @lemonade_server from @AIatAMD, just merged for Strix Halo: • Runs Qwen3.8-Flash-Next with v2 quants • Pinned to the Halogen 0.18.22 release • Tested in CI on the full model Thanks, Lemonade! github.com/lemonade-sdk/lemo…

Halogen 0.18.23: the LFM3 family from @liquidai now runs on the Strix Halo NPU • LFM3-VL-2B: pictures and video • LFM3-Audio-2B: speech in and speech out • LFM3-Omni-2B: every medium on one model • Fix: replies no longer invent a user turn github.com/peonist-ai/haloge…

Another excellent video from @dcapitella Thanks for including Halogen! Strix Halo vs. two Intel Arc Pro B70s on Qwen3.8-Flash-Next: • ~64 tok/s at 64K context • 1,217 tok/s prompt processing • Close in generation, faster at prompt processing youtu.be/Rxh8ouzTEbM?t=1123

Wendell’s @Level1Techs review of the new @gmktecdotcom EVO-X5 Pro: with Halogen, Qwen3.8-Flash-Next on the Ryzen AI Max+ 495 runs at parity with DGX Spark. Thanks Wendell! youtu.be/YbIX2AWCqB8?t=621

Run your own @liquidai d1-2B on the @AIatAMD Strix Halo NPU. Halogen 0.18.22 is out. • Up to 16 questions on text, images or video in one pass • Finds objects in photos with bounding boxes • ~0.35 s per image question github.com/peonist-ai/haloge…

Run your own @liquidai LFM3-1.7B on the @AIatAMD Strix Halo NPU. Halogen 0.18.21 is out. Your checkpoint or fine-tune, up to ~38 tok/s Full 262k context Long NPU requests no longer stall behind a reply github.com/peonist-ai/haloge…

Halogen 0.18.20 for Strix Halo is out. • 2 requests at once ~20% faster, 3 at once ~9% • JSON schemas now work on requests with images • Strict tools enforced with images too • Clear NPU error on old XRT github.com/peonist-ai/haloge…

Running Qwen3.8-Flash-Next on Strix Halo? Halogen 0.18.19 is out. • ~3% faster with 3 requests at once • No more 64-image cap for screenshot agents • Claude Code auto-compacts long prompts • Tool-call fixes #StrixHalo #LocalLLM #qwen github.com/peonist-ai/haloge…

Halogen 0.18.18 is out. • Claude Code sessions with MCP tools keep their prompt cache • ggml-org's official IQ4_NL GGUF now loads • Short requests start during long prompts • Tool-call args with </tool_call> arrive whole Same outputs, same speed. github.com/peonist-ai/haloge…

Halogen 0.18.17 is out. Agents sharing a prompt no longer swap turns on a full KV pool Claude Code MCP tool search works on /v1/messages Tool-call args with markup arrive intact /v1/models reports image support Same outputs, same speed. github.com/peonist-ai/haloge…