# Devstral Small 2 vs Nanbeige4.3-33B (slim)

> Devstral Small 2 and Nanbeige4.3-33B score within a point of each other for open-weight models you run yourself, 61 and 60.8 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b.md (~9,500 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b
- 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 and Nanbeige4.3-33B score within a point of each other on agent readiness, 61 (C) and 60.8 (C). Nanbeige4.3-33B leads on 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
- Nanbeige4.3-33B: C 60.8, rank #86 of 160 open-weight models · https://www.anchorterminal.com/tools/nanbeige-4-3-33b.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 80.
- Nanbeige4.3-33B, good for Agents with a 32 GB GPU (INT4) or more, or the 128 GB reference machine at BF16, that want an Apache-tagged 33B model for long coding and tool loops. Ahead on Agent interface, 85 against 65; Documentation and upkeep, 56 against 46.

| Category | Devstral Small 2 | Nanbeige4.3-33B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 80 |
| Risk (20%) | 60 | 60 |
| Agent interface (10%) | 65 | 85 |
| Documentation and upkeep (10%) | 46 | 56 |

| Fact (where they differ) | Devstral Small 2 | Nanbeige4.3-33B |
| --- | --- | --- |
| Vendor | Mistral AI | Nanbeige LLM Lab (BOSS Zhipin) |
| Licence | Apache-2.0 | Apache-2.0 (Hub metadata only; the repository has no LICENSE file) |
| Last release | 2026-07-15 | 2026-10-31 |

Why the edge:
- Agent interface, Nanbeige4.3-33B +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.); Nanbeige4.3-33B 85 (The chat template earns 20, Jinja in tokenizer_config.json.)
- Reach, Devstral Small 2 +10: 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.); Nanbeige4.3-33B 80 (Memory earns 20, since Nanbeige's INT4 build is 22.57 GB, about 27 GB with a fifth added, which fits 32 GB.)
- Documentation and upkeep, Nanbeige4.3-33B +10: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Nanbeige4.3-33B 56 (The model card earns 11, with intended use, parameters, context and languages but no limitations, architecture or cut-off.)