@TeksEdge: Been testing Orinth-1.0-35B to see how it stacks up with Qwen3.6-35B over a day's use. Anecdotally, it works as well as…
Summary
A user reports that Ornith-1.0-35B matches Qwen3.6-35B in performance but excels at planning and long task execution, while the developer announces the open-source Ornith-1.0 family of LLMs specialized for agentic coding.
View Cached Full Text
Cached at: 06/28/26, 06:01 AM
Been testing Orinth-1.0-35B to see how it stacks up with Qwen3.6-35B over a day’s use. Anecdotally, it works as well as Qwen3.6-35B Q4, but its planning and long task executions are better. I can also run a slightly higher quant on my hw (Q5 w/128K cx) https://t.co/8Ou17xeorc
Ornith (@ornith_): Aloha! 🌺 Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.
Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. It achieves state-of-the-art performance among open-source models of comparable size on
Similar Articles
@no_stp_on_snek: a new 35B coder dropped (Ornith-1.0) and a promo blog says it "crushes" the benchmarks. my first instinct was benchmaxx…
A new 35B coding model, Ornith-1.0, is compared against Qwen3.6-35B on custom tests. The user finds Ornith-1.0 to be genuinely stronger for long-horizon agentic coding, resisting bad context and finishing large tasks, but it is more cautious and verbose, sometimes over-gating simple requests.
@ItsmeAjayKV: Quick update: I tried Ornith-1.0-35B-Q5_K_M on my 3090, and i have mixed feelings. The good: it's really fast. I measur…
User tests Ornith-1.0-35B on an RTX 3090, finding fast inference speeds (1560 tok/s prompt, 78 tok/s generation) but consistently worse coding performance on Three.js tasks compared to Qwen 3.6, even after multiple attempts.
@malikwas1f: Ornith-1.0-35B: a Qwen3.6-35B-A3B coding fine-tune that edges the base on real coding (aider 15/30 vs 13) — full 262K a…
Announces Ornith-1.0-35B, a coding fine-tune of Qwen3.6-35B-A3B that slightly outperforms the base model on aider benchmarks. Also promotes the club-3090 repository for running LLMs on RTX 3090s.
@MiaAI_lab: The Orinth-1.0-35b MoE looks way better than the Qwen 3.6 35b, especially in Terminal-Bench 2.1 & SWE Atlas.
The Orinth-1.0-35b MoE outperforms Qwen 3.6 35b on Terminal-Bench 2.1 and SWE Atlas benchmarks.
@no_stp_on_snek: one last thing: the real downside i found testing Ornith-1.0 (the new agentic coder): it over-gates legitimate work. on…
A tester reports that the new Ornith-1.0 agentic coder model over-gates legitimate work by demanding excessive prerequisites, a trade-off from its cautious training, while stock Qwen3.6 executes simple tasks directly.