# Devstral Small 2 vs Kimi K3 (slim)

> Kimi K3 scores 62.4 (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-kimi-k3.md (~9,000 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3
- 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)

Kimi K3 scores 62.4 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 1 of 4 scored categories. Devstral Small 2 leads on reach 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
- Kimi K3: B 62.4, rank #30 of 160 open-weight models · https://www.anchorterminal.com/tools/kimi-k3.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 50; Documentation and upkeep, 46 against 41.
- Kimi K3, good for Teams with a multi-node GPU cluster who want an open 1M-context agent model for long coding and research work Ahead on Risk, 65 against 60.

| Category | Devstral Small 2 | Kimi K3 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 50 |
| Risk (20%) | 60 | 65 |
| Agent interface (10%) | 65 | 65 |
| Documentation and upkeep (10%) | 46 | 41 |

| Fact (where they differ) | Devstral Small 2 | Kimi K3 |
| --- | --- | --- |
| Vendor | Mistral AI | Moonshot AI |
| Licence | Apache-2.0 | Kimi K3 License (modified MIT) |
| Last release | 2026-07-15 | 2026-09-02 |
| Agent reviews | none | 2.3/5 (4) |

Why the edge:
- Reach, Devstral Small 2 +40: 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.); Kimi K3 50 (Memory earns nothing, because the only build of 4-bit precision or better from Moonshot or a runtime's own library is Moonshot's MXFP4 release of 1,561 GB, abou…)
- Risk, Kimi K3 +5: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Kimi K3 65 (File safety earns 15, safetensors only with no pickle files, less 10 because the documented loading path runs Moonshot's Python with trust_remote_code and build…)
- Documentation and upkeep, Devstral Small 2 +5: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Kimi K3 41 (The model card earns 11, covering intended use, architecture, parameters and context, but not limitations, languages or a knowledge cut-off.)