Ornith
No written verdict yet. Here is what commenters said.
14recommend
1warn against
Jun 25, 2026first mention
Oct 15, 2026latest mention
Latest: Ornith 1.570% recommend · 10% warn · 10 people
By version sentiment of people who named that release, latest release first
VersionSentimentPeopleFirst seen
recommenduses or compareswarns
Versions with at least 5 people. 4 people didn't name a version. Small samples swing a lot, so read the counts too. Compare all models →
Why people recommend it
“it's usable for real coding and sys admin work, and works great in opencode”
“I run these two Qwen model variations successfully”
Show 3 more
“where I run the less quantised versions of these for higher quality results”
“i still miss the speed of that moe”
Caveats and dissent
“Please check your download links, it get 400 Bad Request”
Often compared with
Who recommends it in their own words
Threads where it came up
- Ornith-1.0: self-improving open-source models for agentic coding 4 mentions
- Ornith-1.5: From Self-Scaffolding to Self-Improvement 3 mentions
- Anthropic Subscriptions Offer 5x+ More Value Than OpenAI 2 mentions
- Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s 2 mentions
- Run Qwen3.8 27B locally: real numbers from my Mac Studio 2 mentions
- Qwen 3.6 27B is the sweet spot for local development 2 mentions
Also written as Ornith, Ornith-1.5, Ornith-1.5-35B-A3B, Ornith 1.5 35B. Data: ornith.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 24
“it's usable for real coding and sys admin work, and works great in opencode”
“I run these two Qwen model variations successfully”
“where I run the less quantised versions of these for higher quality results”
“I prefer https://ornith.ai/ornith_1_5.html to Qwen 3.8 not only because it is much faster on my hardware”
“Any other task, I still use Ornith 1.5 35B that throws 20t/sec”
“(my personnal favorite)”
“i still miss the speed of that moe”
“it feels like an improvement.”
“my inference company has actually started offering Ornith1.5 today for 9B and 35B A3B”
“It's now my go-to model for quick inquiries.”
“my new daily driver is Ornith-1.5-35B-A3B-MLX-4bit. I recommend giving that a whirl”
“Ornith1.5-35B-A3B I've been running (and quite happy about).”
“Please check your download links, it get 400 Bad Request”
“Ornith1 (9B) was a really nice model.”
“the subtlety and nuance it showed in its response was very surprising to me”
“it did a little better than Qwen 9B”
“local/ornith-1.0-35b”
“There's definitely some latent capability in there that arguably exceeds Qwen 3.6”
“https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/config.json#L3”
“From what I personally tested Ornith-1.0 35B is slightly better than Qwen-3.6 35B.”
The Ornith folks say they're doing that, but haven't released the Gemma-based 31b yet (https://github.com/deepreinforce-ai/Ornith-1). But, also, the Qwen-based 35b MoE Ornith version performs worse than Qwen 3.6 and Qwen AgentWorld on my benchmarks (which are focused on finding security bugs, so not exactly the same as agentic coding, but closely related skills). That said, the reason they're able to release Ornith b
“Sure.”
“I'm pretty impressed with it”
“Ornith achieves SOTA performance among open-source models of comparable size”