Accelerating LLM Startup on AMD Ryzen AI with Two-Phase Custom Op Initialization
…run Qwen3.5 9B–122B on Ryzen™ AI Max+ with 128GB UMA and Ollama, with generation benchmarks and a clear UMA setup path on Ubuntu/ROCm. May 24, 2026 LLM-D Serving…
Search
Tracked topic
Qwen3
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
Live now
Show HN: I made a Raspberry with Qwen my local car AI
People also ask
What’s New in Qwen 3.8?
For the first time, Qwen3.8 brings a Qwen-Max-class model to open release. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Beyond answering harder questions, Qwen3.8 is designed to carry complex, multi-step tasks through to completion with greater reliability. Qwen3.8 features the following enhancements: Core Capabilities: Comprehensive improvements across coding, professional work, research, and long-horizon agentic tasks. Agent Execution: Stronger autonomous planning and better ha
Day 0 Support for Qwen 3.8 on AMD Instinct GPUsAgent Computers: Pay Once for Cloud-Grade Intelligence
…In agentic terminal benchmarks, compact open models are now competitive with leading cloud models for many practical tasks. Qwen 3.6 35B A3B, for example, demonstrates that a local model can deliver…
AMD Primus: Train AI Models at Scale
…ROCm 7 Accelerating Training Improvement DeepSeek-V3-16B DeepSeek-V2-Lite Qwen3-30B-A3B Release-to-Release: Performance Improvement 2.01x 2.54x 2.76x On Average 2.4X faster than previous…
Dayhoff Health, AMD Accelerate Genomic Analysis by up to 330x
…August 16, 2026 Run Qwen 3.8 27B on AMD Ryzen™ AI Max Agentic PCs and Radeon ™ GPUs Qwen3.8 27B arrives with Day 0 support on AMD Ryzen™ AI processors and…
Run Hermes Agent Locally on AMD Ryzen™ AI Max+ Processors and Radeon™ GPUs
…August 16, 2026 Day 0 Support for Qwen 3 8 on AMD Instinct GPUs AMD is excited to announce Day-0 support for Alibaba's latest Qwen 3.8 model family on…
GEAK v4: From Faster Kernels to Faster Workloads
…Verification Kernel benchmark. Kernel benchmark plus end-to-end serving benchmark. Knowledge base RAG-style knowledge base and reverse knowledge. perf_knowledge: structured kernel optimization knowledge across operators, backends, GPU generations, dtypes…
ROCm™ AI Developer Hub
…Personal AI Agent with OpenClaw and Qwen3.5-122B Deploy a fully local AI agent on AMD Instinct™ MI300X GPU. Kernel development with Triton Set up the Triton development environment and optimize…
Accelerate llama.cpp on AMD EPYC: ZenDNN Delivers Up to 4.5x the Prompt Processing
…August 16, 2026 Day 0 Support for Qwen 3 8 on AMD Instinct GPUs AMD is excited to announce Day-0 support for Alibaba's latest Qwen 3.8 model family on…
Run Hugging Face Models on AMD GPUs with One Click
…Start with Hugging Face Models To try this workflow, start from the AMD Model Collection Page . In this example, search for and open the Qwen3.6-35B-A3B model page . Step 2…
Vibe Coding with Local Models
…July 23, 2026 Benchmarking AI Systems: from Model Metrics to Real-World Performance The agentic AI stack has evolved to fast multi-model orchestration, tool-augmented reasoning, and long-running inference chains…