# Cosmos-Reason2-2B vs Devstral Small 2 (slim)

> Devstral Small 2 scores 61 (C) to Cosmos-Reason2-2B's 59.5 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2.md (~9,300 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2.json · canonical https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2
- 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 Cosmos-Reason2-2B's 59.5 (C), and leads in 2 of 4 scored categories. Both do open-weight models you run yourself.

- Cosmos-Reason2-2B: C 59.5, rank #95 of 160 open-weight models · https://www.anchorterminal.com/tools/cosmos-reason2-2b.min.md
- Devstral Small 2: C 61, rank #60 of 160 open-weight models · https://www.anchorterminal.com/tools/devstral-small-2.min.md
- Cosmos-Reason2-2B, good for Agents that need a small local model to reason over camera footage and images for robotics, driving or smart spaces
- 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 65; Documentation and upkeep, 46 against 39.

| Category | Cosmos-Reason2-2B | Devstral Small 2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 90 |
| Risk (20%) | 60 | 60 |
| Agent interface (10%) | 65 | 65 |
| Documentation and upkeep (10%) | 39 | 46 |

| Fact (where they differ) | Cosmos-Reason2-2B | Devstral Small 2 |
| --- | --- | --- |
| Vendor | NVIDIA | Mistral AI |
| Licence | NVIDIA Open Model License (custom, commercial use allowed, not an OSI licence); built on Qwen3-VL-2B-Instruct under Apache 2.0 | Apache-2.0 |
| Last release | 2026-03-10 | 2026-07-15 |
| Terms last updated | 2025-10-24 | no document linked |
| Customer content may train models | yes | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Reach, Devstral Small 2 +25: Cosmos-Reason2-2B 65 (Memory earns the full 30 because the BF16 file is 4.9 GB, about 5.9 GB with the fifth added, though NVIDIA itself asks for 24 GB of GPU memory.); 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.)
- Documentation and upkeep, Devstral Small 2 +7: Cosmos-Reason2-2B 39 (The card misses languages and a cut-off (14).); Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.)