# Devstral Small 2 vs Hy3 (slim)

> Hy3 scores 62.6 (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-hy3.md (~8,800 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3
- 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)

Hy3 scores 62.6 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach. 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
- Hy3: B 62.6, rank #28 of 160 open-weight models · https://www.anchorterminal.com/tools/hy3.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 70.
- Hy3, good for Teams with an 8-GPU server who want an agent-tuned MoE model under plain Apache 2.0 Ahead on Agent interface, 75 against 65; Documentation and upkeep, 56 against 46.

| Category | Devstral Small 2 | Hy3 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 70 |
| Risk (20%) | 60 | 60 |
| Agent interface (10%) | 65 | 75 |
| Documentation and upkeep (10%) | 46 | 56 |

| Fact (where they differ) | Devstral Small 2 | Hy3 |
| --- | --- | --- |
| Vendor | Mistral AI | Tencent (Hy team) |
| Last release | 2026-07-15 | 2026-07-20 |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Reach, Devstral Small 2 +20: 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.); Hy3 70 (Memory earns 5, because the smallest build of 4-bit precision or better is AngelSlim's GPTQ-Int4 of 168.5 GB, about 202 GB with the fifth added, which is within…)
- Agent interface, Hy3 +10: 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.); Hy3 75 (The chat template earns 20, a chat_template.jinja in the repository.)
- Documentation and upkeep, Hy3 +10: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Hy3 56 (The model card earns 11, covering intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.)