Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
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 GPUs… Typical VRAM Usage by Popular Models LLM DeepSeek R1 Distill Qwen 32B Q6 28GB Mistral Small 3.1 24B Instruct 2503 Q8 27GB Text to Image Flux.1 Schnell 24GB SD 3.5 Medium 17GB See endnote RPW-496 Massive Gains for Massive Models Up to 5× Faster with 32GB VRAM 100% 361% 437% 454% 447% 496% Phi 3.5 Mo… …
… AMD Ryzen™ AI Halo 2,3 GLM 4.7 Flash-30B-A3B +14% GPT-OSS -120B +7% Qwen 3.5-122B-A10B +12% Qwen 3.6-35B-A3B +4% NVIDIA DGX Spark AMD Ryzen AI Halo Performance Tokens/Second NVIDIA DGX Spark Supports Linux Only Lower Tok/Sec per $ No NPU AMD Ryzen AI Halo Supports Windows and Linux OS Leadership … …
… Figure 3: Qwen code deployment Step 1: Install node.js bash curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash nvm install --lts nvm use --lts node -v npm -v Step 2: install Qwen code bash Install Qwen Code npm install -g @qwen-code/qwen-code@latest verify qwen --versio… …
… Run the following commands on your droplet to start your model inference: docker run -d \ --name sglang server \ --ipc=host \ --privileged \ --device=/dev/kfd \ --device=/dev/dri \ -p 8090:8090 \ lmsysorg/sglang:v0.5.9-rocm700-mi30x \ python3 -m sglang.launch server \ --model-path Qwen/Qwen3.5-122B… …
… How many eggs does she sell?\nAnswer:", "max tokens": 64, "temperature": 0 Step 4 Optional — Accuracy Evaluation GSM8K MXFP4 on MI355X TP8, single node SGLang built-in benchmark: python3 -m sglang.test.run eval \ --port 9001 \ --model /mnt/models/Qwen3.8-2.4T-A95B-Quark-MXFP4 \ --eval-name gsm8k \ … …
… AIM Catalog of AI Models Existing models Added in version 1.8 Cohere Labs Command A Reasoning 08 2025 DeepSeek DeepSeek R1 DeepSeek R1 0528 DeepSeek V3.1 DeepSeek V3.1 Terminus Qwen AI Qwen3 235B A22B Mistral AI Ministral 3 14B Instruct 2512 Qwen3 32B Mistral Large 3 675B Instruct 2512 Meta Llama 3… …
… August 12, 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 AMD Instinct™ MI300X, MI325X, and MI355X GPUs. …
… 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 Radeon™ graphics cards. Run the latest Qwen model locally with LM Studio on supported AMD hardware. …
… 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 AMD Instinct™ MI300X, MI325X, and MI355X GPUs. …
… Download the vllm docker image and Lanch a vllm docker container docker pull rocm/vllm:rocm6.2 mi300 ubuntu20.04 py3.9 vllm 0.6.4 export HF TOKEN="your personal Hugging Face token to access gated models" docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G \ --securit… …