24 engineers on Hacker News describe using Qwen first-hand: 12 endorse it, 3 regret it, 4 are mixed.
“I tried a local Qwen model but my poor old 1660 Ti did not enjoy it, and it wasn't all that useful.”
regret · personal · einhard · 2026-11-05 · source ↗ · wrong label?“GLM, Qwen and Deepseek are incredible tool callers, but their prose is insufferable.”
mixed · personal · guhcampos · 2026-11-05 · source ↗ · wrong label?“I've been running something similar for few weeks, but with Qwen3.8-Flash-Next.”
endorse · personal · 0.1 yr · Roark66 · 2026-11-02 · source ↗ · wrong label?“It does everything I want it to!”
endorse · personal · 0.17 yr · trog · 2026-11-01 · source ↗ · wrong label?“I would not trust them to evaluate 4 different libraries from scratch unless I gave them extremely specific benchmarks to run”
mixed · personal · Aurornis · 2026-10-30 · source ↗ · wrong label?“The model itself (Qwen 3.8 27B specifically) can handle being interrupted just fine and i often interrupt it to clarify things”
endorse · personal · badsectoracula · 2026-10-25 · source ↗ · wrong label?“I'm very happy with the outputs one of the Flash models has been generating.”
endorse · personal · hughc · 2026-10-20 · source ↗ · wrong label?“I have been using it locally and it's just such a great little model to work with.”
endorse · personal · bitexploder · 2026-10-19 · source ↗ · wrong label?“I've been using Qwen 3.7 Plus on it and having great results for $10 per month with my personal usage.”
endorse · personal · john01dav · 2026-10-17 · source ↗ · wrong label?“Qwen is faster and seems to be much better at coding tasks.”
endorse · personal · kamranjon · 2026-10-17 · source ↗ · wrong label?“Qwen, gemma etc all have terrible non-uniform probabilities; in my testing, Jev's probability scores perform much, much better.”
regret · personal · mediaman · 2026-10-15 · source ↗ · wrong label?“I use Qwen quants in production for fast inference but I disable thinking and have them fine tuned”
mixed · production · AustinDev · 2026-10-10 · source ↗ · wrong label?“I accidentally let qwen wipe my 60tb nas the other day”
regret · personal · swozey · 2026-10-05 · source ↗ · wrong label?“I (we) run Qwen3.8-27B-FP8 on a DGX Spark box... it runs quite well but it is a quantised jobbie”
mixed · personal · gerdesj · 2026-09-03 · source ↗ · wrong label?“The latest qwen 3.8 model has a 95% success tool call rate during internal testing and about 94% real world.”
endorse · production · hadlock · 2026-09-02 · source ↗ · wrong label?“Qwen 3.8 27b in my experience is more than capable of churning out features overnight with the right tools”
endorse · production · nejch · 2026-08-30 · source ↗ · wrong label?“Qwen 3.6 27B is an anomalously strong all-around model for its size, but when we run our evaluations”
endorse · production · gertlabs · 2026-06-23 · source ↗ · wrong label?“We are doing some weird q4 on 3090s now that is surprisingly good (for qwen).”
endorse · production · yolo-auto · 2026-06-14 · source ↗ · wrong label?“I've been using Qwen3 Coder 30b quantized down to IQ3_XSS to fit in < 16gb vram.”
endorse · personal · ineedasername · 2025-12-22 · source ↗ · wrong label?“It runs supported open-weights models; we started with Gemma 4 and Qwen3.8.”
neutral · production · giarec · 2026-10-30 · source ↗ · wrong label?“So far I think I have some small RAG model in a demo or the very small qwen models.”
neutral · personal · ashkankiani · 2026-10-27 · source ↗ · wrong label?“We run a few Qwen models locally and pretty much have them pegged all day.”
neutral · production · trollbridge · 2026-06-23 · source ↗ · wrong label?“so we could switch between DeepSeek v4, GLM 5.1, and Qwen 3.7 models”
neutral · production · ignoramous · 2026-06-03 · source ↗ · wrong label?“We run Qwen3 32b which in some benchmarks is equivalent to GPT 4.1-mini or Gemini 2.5 Flash.”
neutral · production · 0.08 yr · kgeist · 2025-07-06 · source ↗ · wrong label?