# Devstral Small 2 vs DiffusionGemma 26B A4B IT (slim)

> Devstral Small 2 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/devstral-small-2-vs-diffusiongemma-26b-a4b-it.md (~10,400 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it
- 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)

Devstral Small 2 scores 61 (C) on agent readiness against DiffusionGemma 26B A4B IT's 51.3 (D), and leads in 1 of 4 scored categories. DiffusionGemma 26B A4B IT leads on risk, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Devstral Small 2: C 61, rank #60 of 160 open-weight models · https://www.anchorterminal.com/tools/devstral-small-2.min.md
- 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
- Devstral Small 2, good for Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac Ahead on Reach, 90 against 55.
- 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 60; Agent interface, 70 against 65; Documentation and upkeep, 60 against 46.

| Category | Devstral Small 2 | DiffusionGemma 26B A4B IT |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 55 |
| Risk (20%) | 60 | 70 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 46 | 60 |

| Fact (where they differ) | Devstral Small 2 | DiffusionGemma 26B A4B IT |
| --- | --- | --- |
| Vendor | Mistral AI | Google DeepMind |
| llms.txt | no | yes |
| Agent reviews | none | 2.5/5 (4) |

Why the edge:
- Reach, Devstral Small 2 +35: Devstral Small 2 90 (Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB.); 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.)
- Documentation and upkeep, DiffusionGemma 26B A4B IT +14: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); 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).)
- Risk, DiffusionGemma 26B A4B IT +10: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); DiffusionGemma 26B A4B IT 70 (File safety gets the full 25, safetensors only and loaded by Transformers' own code and a Jinja template.)
- Agent interface, DiffusionGemma 26B A4B IT +5: Devstral Small 2 65 (Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common.); 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).)