Unsloth and AMD bring NPU inference to 100+ agentic AI apps, 2–4× less power
danielhanchen · x · 2026-11-19
Unsloth partnered with AMD to enable local model inference on AMD XDNA 2 NPUs — the first NPUs supported by Unsloth Desktop — bringing NPU acceleration to 100+ compatible agentic AI apps.
- NPUs use 2–4× less power per token than traditional GPUs
- Supports Ryzen AI 300 (Strix/Krackan Point), Ryzen AI Max (Strix Halo), Ryzen AI 400 (Gorgon Point) and future NPU devices
- Features: streaming LLM runs on NPU with reasoning, vision, tools, skills, MCP servers, web search and local-file coding; an API endpoint to connect apps/scripts to NPU models; offloading local inference to free memory on other processors
Related event: AMD XDNA 2 NPU Gains Unsloth Desktop Support for Local Agent Apps(2 posts)→
More from coding & agent
- CoHDL turns PCB schematics into typed source code that compiles to netlists, built for AI — juntao · 2026-11-19
- Watch an AI agent make real phone calls: full demo with live transcripts and human handoff — mattyp · 2026-11-19
- Hands-on coding test: Tencent's Hy4 Flash beats DeepSeek by 12x on same task — HeyToha · 2026-11-19
- LangChain's Max Agency podcast returns for season 2 with Clay's Head of AI — LangChain · 2026-11-19
- Garry Tan's "Personal AGI" is a folder of markdown files — 220,000 pages, 400x his 2013 output — jasonkneen · 2026-11-19
- Same weights, 3x score: Gemini 4 Neon jumps 12.8%→39% on SWE-sweep by swapping the harness — Delicious_Character6 · 2026-11-19