# DiffusionGemma 26B A4B IT vs Ornith-1.5-122B (slim)

> Ornith-1.5-122B scores 61 (C) to DiffusionGemma 26B A4B IT's 51.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-122b.md (~10,300 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-122b.json · canonical https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-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 DiffusionGemma 26B A4B IT's 51.3 (D), and leads in 2 of 4 scored categories. DiffusionGemma 26B A4B IT leads on risk and documentation and upkeep. Both do open-weight models you run yourself.

- DiffusionGemma 26B A4B IT: D 51.3, rank #143 of 160 open-weight models · https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.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
- DiffusionGemma 26B A4B IT, good for Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4 Ahead on Risk, 70 against 50; Documentation and upkeep, 60 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 Reach, 75 against 55; Agent interface, 85 against 70.

| Category | DiffusionGemma 26B A4B IT | Ornith-1.5-122B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 55 | 75 |
| Risk (20%) | 70 | 50 |
| Agent interface (10%) | 70 | 85 |
| Documentation and upkeep (10%) | 60 | 36 |

| Fact (where they differ) | DiffusionGemma 26B A4B IT | Ornith-1.5-122B |
| --- | --- | --- |
| Vendor | Google DeepMind | Ornith |
| Licence | Apache-2.0 | MIT |
| llms.txt | yes | no |
| Last release | 2026-07-15 | 2026-10-24 |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Documentation and upkeep, DiffusionGemma 26B A4B IT +24: DiffusionGemma 26B A4B IT 60 (The card covers all seven points (20), and the training data is a general description with a January 2025 cut-off (10).); 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, Ornith-1.5-122B +20: DiffusionGemma 26B A4B IT 55 (Memory earns 15 because the only Google build is 51.7 GB of BF16, about 62 GB with the fifth added, which needs the 64 GB band.); 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, DiffusionGemma 26B A4B IT +20: DiffusionGemma 26B A4B IT 70 (File safety gets the full 25, safetensors only and loaded by Transformers' own code and a Jinja template.); 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…)
- Agent interface, Ornith-1.5-122B +15: DiffusionGemma 26B A4B IT 70 (The chat template is in the repository (20) and handles several tool calls in one turn, and the card names function calling as trained (20).); Ornith-1.5-122B 85 (Chat template 20, a Jinja file in the repository.)