# Granite 4.2 3B vs Ornith-1.5-122B (slim)

> Ornith-1.5-122B scores 61 (C) to Granite 4.2 3B's 59.8 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/granite-4-2-3b-vs-ornith-1-5-122b.md (~9,300 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/granite-4-2-3b-vs-ornith-1-5-122b.json · canonical https://www.anchorterminal.com/compare/granite-4-2-3b-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)

Ornith-1.5-122B scores 61 (C) on agent readiness against Granite 4.2 3B's 59.8 (C), and leads in 0 of 4 scored categories. Granite 4.2 3B leads on reach, risk and documentation and upkeep. Both do open-weight models you run yourself.

- Granite 4.2 3B: C 59.8, rank #92 of 160 open-weight models · https://www.anchorterminal.com/tools/granite-4-2-3b.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
- Granite 4.2 3B, good for Agents on small hardware that want a permissive reasoning model for tool calls and coding, with thinking they can switch off Ahead on Reach, 95 against 75; Risk, 55 against 50; Documentation and upkeep, 92 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

| Category | Granite 4.2 3B | Ornith-1.5-122B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 95 | 75 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 92 | 36 |

| Fact (where they differ) | Granite 4.2 3B | Ornith-1.5-122B |
| --- | --- | --- |
| Vendor | IBM | Ornith |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-10-20 | 2026-10-24 |
| Agent reviews | 3.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Granite 4.2 3B +56: Granite 4.2 3B 92 (The card covers everything but a knowledge cut-off (17).); 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, Granite 4.2 3B +20: Granite 4.2 3B 95 (Memory earns the full 30, since IBM's 4-bit MLX build is 2.07 GB and Ollama's Q4_K_M build 2.2 GB, about 2.5 to 2.6 GB with the fifth added.); 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…)
- Risk, Granite 4.2 3B +5: Granite 4.2 3B 55 (File safety gets 15 of 25, safetensors only, less 10 because the card's vLLM command loads the repository's parser plugin.); 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…)