# occamy-1.0 vs Ornith-1.5-122B (slim)

> occamy-1.0 and Ornith-1.5-122B score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/occamy-1-0-vs-ornith-1-5-122b.md (~9,200 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/occamy-1-0-vs-ornith-1-5-122b.json · canonical https://www.anchorterminal.com/compare/occamy-1-0-vs-ornith-1-5-122b
- 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)

occamy-1.0 and Ornith-1.5-122B score within a point of each other on agent readiness, 61 (C) and 61 (C). Ornith-1.5-122B leads on agent interface. Both do open-weight models you run yourself.

- occamy-1.0: C 61, rank #59 of 160 open-weight models · https://www.anchorterminal.com/tools/occamy-1-0.min.md
- Ornith-1.5-122B: C 61, rank #81 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-122b.min.md
- occamy-1.0, good for Agents that want an Apache 2.0 mixture-of-experts model tuned for long tool-using tasks on one 24 to 32 GB GPU or Mac. Ahead on Reach, 90 against 75; Risk, 55 against 50; Documentation and upkeep, 74 against 36.
- 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.

| Category | occamy-1.0 | Ornith-1.5-122B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 75 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 70 | 85 |
| Documentation and upkeep (10%) | 74 | 36 |

| Fact (where they differ) | occamy-1.0 | Ornith-1.5-122B |
| --- | --- | --- |
| Vendor | Accio (Accio-Lab) | Ornith |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-10-02 | 2026-10-24 |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Documentation and upkeep, occamy-1.0 +38: occamy-1.0 74 (Model card 14 of 20, languages and a knowledge cut-off are missing.); 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.)
- Reach, occamy-1.0 +15: occamy-1.0 90 (Memory 25 of 30, Accio's MLX mxfp4 build is 18.4 GB, 22.1 GB with a fifth added, and its IQ4_XS GGUF needs 22.5 GB, both within 24 GB.); 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…)
- Agent interface, Ornith-1.5-122B +15: occamy-1.0 70 (Chat template 20, the base's Jinja template in the repository.); Ornith-1.5-122B 85 (Chat template 20, a Jinja file in the repository.)
- Risk, occamy-1.0 +5: occamy-1.0 55 (File safety 25, safetensors only and nothing from the repository runs to load it or build prompts.); 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…)