# Ornith-1.5-122B vs Qwen3.6-35B-A3B (slim)

> Qwen3.6-35B-A3B scores 62.7 (B) to Ornith-1.5-122B's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/ornith-1-5-122b-vs-qwen3-6-35b-a3b.md (~9,800 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/ornith-1-5-122b-vs-qwen3-6-35b-a3b.json · canonical https://www.anchorterminal.com/compare/ornith-1-5-122b-vs-qwen3-6-35b-a3b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Qwen3.6-35B-A3B scores 62.7 (B) on agent readiness against Ornith-1.5-122B's 61 (C), and leads in 2 of 4 scored categories. Ornith-1.5-122B leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Ornith-1.5-122B: C 61, rank #81 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-122b.min.md
- Qwen3.6-35B-A3B: B 62.7, rank #27 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-6-35b-a3b.min.md
- Ornith-1.5-122B, good for Local coding and terminal agents on a 128 GB unified-memory machine or a 96 GB GPU setup, where a clear licence file and an answering publisher aren't required Ahead on Agent interface, 85 against 70; Documentation and upkeep, 36 against 31.
- Qwen3.6-35B-A3B, good for Agents with a 32 GB or larger machine that want a quick, permissively licensed coding and tool-calling cousin with vision. Ahead on Reach, 85 against 75; Risk, 55 against 50.

| Category | Ornith-1.5-122B | Qwen3.6-35B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 75 | 85 |
| Risk (20%) | 50 | 55 |
| Agent interface (10%) | 85 | 70 |
| Documentation and upkeep (10%) | 36 | 31 |

| Fact (where they differ) | Ornith-1.5-122B | Qwen3.6-35B-A3B |
| --- | --- | --- |
| Vendor | Ornith | Alibaba (Qwen team) |
| Licence | MIT | Apache-2.0 |
| Last release | 2026-10-24 | 2026-04-16 |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Agent interface, Ornith-1.5-122B +15: Ornith-1.5-122B 85 (Chat template 20, a Jinja file in the repository.); Qwen3.6-35B-A3B 70 (The chat template earns 20 as a Jinja file in the repository.)
- Reach, Qwen3.6-35B-A3B +10: Ornith-1.5-122B 75 (Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference machine's 107.4 GB, a…); Qwen3.6-35B-A3B 85 (Memory earns 20 because the smallest 4-bit build from a runtime's own library is Ollama's Q4_K_M at 23 GB, which comes to 27.6 GB with the fifth added, so it ne…)
- Risk, Qwen3.6-35B-A3B +5: Ornith-1.5-122B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from…); Qwen3.6-35B-A3B 55 (File safety earns 25 for safetensors only, loaded by the runtimes' own code and a Jinja template with nothing run from the repository.)
- Documentation and upkeep, Ornith-1.5-122B +5: Ornith-1.5-122B 36 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.); Qwen3.6-35B-A3B 31 (The model card earns 11, covering intended use, architecture, parameters and context but not limitations, languages or a cut-off.)