Qwopus
Hacker ApprovedRanked 30 of 39 open-weight language models by recommenders
People recommend Qwopus, a Qwen fine-tune in Opus style, for solid local coding and grunt-work tasks across multiple files. Critics say its marketing overstates it and that results vary between runs.
People recommend Qwopus, a Qwen fine-tune in Opus style, for solid local coding and grunt-work tasks across multiple files. Critics say its marketing overstates it and that results vary between runs.
14 people gave an opinion
- recommend it
- 10
- criticize it
- 4
- approval share
- 71%
Recommended in 7 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 7 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Solid quality and benchmarks
“Rapid MLX team has done some interesting benchmarking that suggests Qwopus 27B is pretty solid.”
Comment from 21 Apr 2026 in “Anthropic says OpenClaw-style Claude CLI usage is allowed again” “It's a nice refinement of the current 27b with slightly better stats.”
Comment from 29 Jun 2026 in “Qwen 3.6 27B is the sweet spot for local development” “I've been pleasantly surprised by its quality”
Comment from 16 Jun 2026 in “Running local models is good now” - Comment from 22 Apr 2026 in “Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model”
Best local results for some users
“the Opus 4.6 distilled versions of the model ("Qwopus") tend to perform better for other tasks”
Comment from 20 Mar 2026 in “MacBook M5 Pro and Qwen3.5 = Local AI Security System” “I have had my best results locally so far from Qwopus”
Comment from 14 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” Runs on modest hardware
“Now I'm feeling pretty good about getting 10-11 tokens/sec running Qwopus 3.6-35B-A3B Q6_K”
Comment from 1 Sep 2026 in “Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s” “Runs the 3bit model faster than the 2bit one runs on my old-ass card”
Comment from 8 Sep 2026 in “Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses”
What people warn about
Each mark is one comment
Claims seen as overhyped
“it seems quite subjective to suggest it's the latest latest or greatest Qwen iteration”
Comment from 13 Apr 2026 in “I ran Gemma 4 as a local model in Codex CLI” “The Qwopus models are marketing.”
Comment from 29 Jun 2026 in “Qwen 3.6 27B is the sweet spot for local development”
Other open-weight language models people recommend
The four most recommended other open-weight language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Qwen 3.8 27B | 1,173 | 426 | 73% | 13 | 2 mo32 owners | Approved |
| Z.ai GLM | 1,043 | 384 | 73% | 13 | 2 mo52 owners | Approved |
| Kimi | 931 | 359 | 72% | 13 | 1 mo26 owners | Approved |
| Gemma 4 | 713 | 249 | 74% | 13 | 1 mo14 owners | Approved |
| QwopusThis page | 10 | 4 | 71% | 7 | — | Approved |
What people said
15 of the 16 comments that mention it, newest first. Each links to the original comment.
“Since AI can't be copywritten, distillation is the way forward to getting rid of these proprietary models.”
“Runs the 3bit model faster than the 2bit one runs on my old-ass card”
“Now I'm feeling pretty good about getting 10-11 tokens/sec running Qwopus 3.6-35B-A3B Q6_K”
“I have had my best results locally so far from Qwopus”
“The Qwopus models are marketing.”
“specifically post-train adapted a bit to run with thinking off”
“It's a nice refinement of the current 27b with slightly better stats.”
“Some fine-tunes like Qwopus-Coder just seem prone to looping”
“the qwopus 27b model is good for grunt work style tasks, even across multiple files”
“I've been pleasantly surprised by its quality”
“60/100 first run, 80/100 on rerun — same prompt, different mistakes”
“how good the qwopus fine tune was”
“Rapid MLX team has done some interesting benchmarking that suggests Qwopus 27B is pretty solid.”
“it seems quite subjective to suggest it's the latest latest or greatest Qwen iteration”
“the Opus 4.6 distilled versions of the model ("Qwopus") tend to perform better for other tasks”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.