Qwen3.8-27B tested: performance between Opus-4.6 and 4.8, good for coding
OwariDa · x · 2026-08-15
Developer OwariDa shares junsong's 1-hour review of Qwen3.8-27B: performance between Opus-4.6 and 4.8, improved tool calling and agentic tasks, usable as main coding agent. OwariDa agrees after 2 hours and is building SuperQwen3.8-27B with NVFP4, MLX MTP, and 6.5bit MTP versions.
More from Models
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- Sakana AI translation outperforms Google and DeepL in Japanese-English benchmarks — SakanaAILabs · 2026-08-24
- Developer haider makes his own LLM tier list after disagreeing with theo's rankings — haider1 · 2026-08-24
- Mystery OxAlpha Beats Claude; Alibaba Raises $10B for AI — 创业邦 · 2026-08-24
- OpenAI and Google cut LLM prices; mystery OxAlpha model beats Claude on DeepSWE — 创业邦 · 2026-08-24
- AI News Digest: DeepSeek Weekend Discounts, GPT-5.6 Sol Price Cut, Alibaba's $10B AI Raise — APPSO · 2026-08-24