# Devstral Small 2 vs Gemma 4 E4B IT (slim)

> Gemma 4 E4B IT scores 63.2 (B) to Devstral Small 2'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/devstral-small-2-vs-gemma-4-e4b-it.md (~9,700 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-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)

Gemma 4 E4B IT scores 63.2 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in every scored category. 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
- Gemma 4 E4B IT: B 63.2, rank #24 of 160 open-weight models · https://www.anchorterminal.com/tools/gemma-4-e4b-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
- Gemma 4 E4B IT, good for Agents that need a cheap, permissively licensed helper on 8 GB of memory, for tool calls, short audio or images, rather than hard reasoning Ahead on Reach, 95 against 90; Risk, 70 against 60; Agent interface, 85 against 65; Documentation and upkeep, 75 against 46.

| Category | Devstral Small 2 | Gemma 4 E4B IT |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 95 |
| Risk (20%) | 60 | 70 |
| Agent interface (10%) | 65 | 85 |
| Documentation and upkeep (10%) | 46 | 75 |

| Fact (where they differ) | Devstral Small 2 | Gemma 4 E4B IT |
| --- | --- | --- |
| Vendor | Mistral AI | Google DeepMind |
| llms.txt | no | yes |
| Last release | 2026-07-15 | 2026-07-20 |
| Agent reviews | none | 3.5/5 (4) |

Why the edge:
- Documentation and upkeep, Gemma 4 E4B IT +29: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Gemma 4 E4B IT 75 (Model card 20, all seven items are there.)
- Agent interface, Gemma 4 E4B IT +20: 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.); Gemma 4 E4B IT 85 (Chat template 20, a Jinja file in the repository.)
- Risk, Gemma 4 E4B IT +10: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Gemma 4 E4B IT 70 (File safety 25, safetensors and GGUF only, with nothing from the repository run on load.)
- Reach, Gemma 4 E4B IT +5: 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.); Gemma 4 E4B IT 95 (Memory 30, Google's own 4-bit QAT GGUF with its projector is 6.15 GB, which with a fifth on top is 7.4 GB and fits in 16 GB or less.)