FULL STORY
Qwen 3.8-27B: From Release to Community Benchmarks
Qwen's newly released 3.8-27B model triggered immediate community testing: bf16 runs show web-design gains over its predecessor, and local benchmarks on 24GB GPUs put its coding agent ahead of rivals including Gemma 4.
2026-08-14 ~ 2026-08-15 · 2 episodes · 4 posts
Episode 1 · Qwen 3.8-27B Released with Improved Performance (2026-08-14, 2 posts)
Qwen 3.8-27B has been released, with users reporting improved performance in web design compared to version 3.6.
- Qwen 3.8 27B Released: Users Share Experiences and Compare with Frontier Models — BarberIcy366 · 2026-08-14
- Benchmark: Qwen 27B 3.8 outperforms 3.6 in web design tasks — ShadyShroomz · 2026-08-15
Episode 2 · Qwen2.5-32B Beats Qwen2 and Gemma 4 in Coding, Agentic Benchmarks (2026-08-14, 2 posts)
Users benchmarked Qwen2.5-32B (dubbed 'Qwen3.8' in posts) against Qwen2-32B and Gemma 4 locally on a 24GB GPU, finding Qwen2.5 leading on coding and agentic benchmarks among the similarly sized open models.
- Qwen3.8 27B vs Qwen3.6 27B vs Gemma 4 31B: Comparing 24GB GPU Options — MaySaki2 · 2026-08-14
- Qwen2.5 vs Qwen2 vs Gemma 4: Benchmarking 30B-class open models — MaySaki2 · 2026-08-15