Qwen

5 pieces on Qwen, including 1 step-by-step guide.

Guides

guides
Shan • 2026-09-24
qwenunslothllama-cpplocal-llmquantizationmtp

Host and Run Qwen3.8-Flash Locally: Complete Unsloth and llama.cpp Deployment Guide

Run Qwen3.8-Flash locally on CPU, unified memory, or GPUs using Unsloth and llama.cpp with Multi-Token Prediction (MTP) for up to 1.7x faster inference.

Read more →

News & Analysis

Qwen 3.8 27B Is Capable but Defaults to Extreme Overthinking
news
Shan • 2026-08-17
Local LLMsOpen WeightsLLM ReasoningCoding AgentsQwen

Qwen 3.8 27B Is Capable but Defaults to Extreme Overthinking

Alibaba's Apache 2.0-licensed 27B vision model fits in 17 GB and handles agents, vision, and code — but its xhigh reasoning default is a trap.

Read more →
Qwen 3.8 27B Is Strong but Overthinks by Default
news
Shan • 2026-08-16
Open WeightsLocal InferenceLLM ReasoningQwenCoding Agents

Qwen 3.8 27B Is Strong but Overthinks by Default

Alibaba's 17 GB Qwen 3.8 27B excels at vision, tool use, and coding agents — but its xhigh reasoning default burns tokens on trivial prompts.

Read more →
news
Shan • 2026-06-03
QwenAlibabaMultimodal AIAI AgentsEnterprise AI

Alibaba Launches Qwen3.7-Plus With Vision, Tool Use, and Agentic Iteration

Qwen3.7-Plus brings image and video understanding, deep reasoning, tool invocation, verification loops, and autonomous iteration to Alibaba's Bailian platform.

Read more →
news
Shan • 2026-05-28
AICoding ModelsQwenAlibaba

Alibaba's Qwen3.7-Max Breaks Into the Top Five on Code Arena

Alibaba's newest Qwen model has climbed into Code Arena's global top five, beating several OpenAI and Google systems in developer-voted coding battles.

Read more →