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…
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
Qwen 3.6 is now much easier to run locally on your Mac, thanks to JetBrains
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 GPUsAMD Powers Next-Generation Agent Computers with New Ryzen AI Halo Developer Platform and Ryzen AI Max PRO 400 Series Processors
…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…
AMD Blogs - News, Announcements, and Technical Articles
…Agent for free on AMD Developer Cloud with Qwen3.5, vLLM, and AMD Instinct™ MI300X GPUs. May 21, 2026 QuickReduce FP4 Quantization and Benchmarking on MI355 — ROCm Blogs Learn how QuickReduce uses…
LLM-D Serving for AMD Instinct GPUs on OCI
…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 From Naive to…
Advancing Windows ML Acceleration with AMD at Microsoft Build 2026
…Strong scores in Procyon® AI Computer Vision Benchmark 2.0 Windows ML achieved excellent scores on the Procyon AI Computer Vision 2.0 benchmark, validating end-to-end performance across a range…
ZenDNN 6.0: FP16 Inference and MoE Acceleration on AMD EPYC™ CPUs
…With ZenDNN 6.0, we move to online serving benchmarks, where requests arrive continuously at varying rates, reflecting real-world deployment conditions. We also adopt multi-instance serving as the primary benchmarking…
Accelerating Applications with AOCL Cryptography
…At startup, strongSwan benchmarks all registered plugins using internal test vectors and selects the fastest one for each algorithm. The throughput scores reported below come from this built-in benchmark (higher is…
Picard BAM Processing: AOCL as a Practical Option for Accelerating Picard Workflows
…5 (default) The same hardware, operating system, Picard version, and input dataset were used for all benchmark runs to ensure a fair comparison. Practical Takeaways Profiling and benchmark results show that AMD…
ROCm.AI: The AI-Native Developer Experience for Building on AMD
…rocm install rocm doctor rocm serve qwen3 rocm update ROCm Console: Telemetry and Diagnostics ROCm Console provides visibility into system and workload state. It surfaces telemetry, logs, runtime status, and diagnostic context…
Win on TCO: How AMD Instinct™ MI355X Achieves Cost-Competitive Distributed Inference Through SGLang with MoRI
…like Qwen3.5-397B-A17B. It also handles TP-mismatch scenarios where prefill and decode use different tensor-parallel degrees, correctly mapping replicated attention heads across ranks. MoRI-IO benchmark on the…