Tracked topic
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… My local stack keeps growing I think this one earns a permanent spot, though not by pushing anything else out. Qwen and Gemma are still doing the bulk of what I need from a local model. …
… 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… …
… One of my tests, though, proved just how incredible local models have become. There are reasons to believe the hype when it comes to the Qwen models; I've had consistently good experiences with Qwen 3.6 27B , and Qwen 3.8 27B is, so far, more of the same but better. …
… In one test, with 90,000 tokens of context and zero contamination, the local model gave the better answer. This isn't local models beating the cloud, because they don't overall . It's messier than that, but Qwen gives it some fantastic competition. …
… 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 \ … …
… View arXiv page View PDF Add to collection Community Qwen3.7-Max/Plus is already live as a closed API — any plans for open-weight releases of the 3.7 family? like 3.6-35B-A3B / 3.6-27B alongside 3.6-Max Would love to run it locally via llama.cpp / GGUF. …
… Related I ditched LM Studio for an open-source alternative — and my local model is doing things it couldn't before It's better in all the ways I needed local AI to be better A quick overview of Qwen and Gemma Why these two ended up in my rotation Qwen 3.5 9B dropped in February as part of the Qwen … …
… Related I finally found a local LLM I want to use every day and it's not for coding Local AI that actually fits into my day Qwen 3.5 4B My unplanned third pick Phi-3.5 mini was supposed to be the third model. …
… Following up on the recent release of Qwen3 , the latest addition to the Qwen family of large language models LLMs , we are thrilled to share our initial performance benchmarking results and use case demos. …
… I suspect that most will bring their own cloud-based subscription, but I was especially curious how a local LLM would handle it instead. Armed with Qwen 3.6 27B Q4 K M with multi-token prediction on a Radeon RX 7900 XTX and deployed with llama.cpp, I was ready to go. …
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.