# Devstral Small 2 vs Nemotron 3 Ultra 550B A55B (slim)

> Nemotron 3 Ultra 550B A55B scores 69.3 (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-nemotron-3-ultra-550b-a55b.md (~10,450 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b
- 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)

Nemotron 3 Ultra 550B A55B scores 69.3 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 3 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
- Nemotron 3 Ultra 550B A55B: B 69.3, rank #9 of 160 open-weight models · https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b.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 55.
- Nemotron 3 Ultra 550B A55B, good for Agents with a multi-GPU Blackwell or Hopper node, or using a hosted endpoint, that want NVIDIA's strongest open model for long agent runs Ahead on Risk, 70 against 60; Agent interface, 90 against 65; Documentation and upkeep, 70 against 46.

| Category | Devstral Small 2 | Nemotron 3 Ultra 550B A55B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 55 |
| Risk (20%) | 60 | 70 |
| Agent interface (10%) | 65 | 90 |
| Documentation and upkeep (10%) | 46 | 70 |

| Fact (where they differ) | Devstral Small 2 | Nemotron 3 Ultra 550B A55B |
| --- | --- | --- |
| Vendor | Mistral AI | NVIDIA |
| Licence | Apache-2.0 | OpenMDW-1.1 |
| Last release | 2026-07-15 | 2026-06-04 |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Reach, Devstral Small 2 +35: 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.); Nemotron 3 Ultra 550B A55B 55 (Memory earns 0, because the smallest 4-bit build, NVIDIA's 352 GB NVFP4, needs about 423 GB with the fifth added, above the 256 GB band, and no runtime library…)
- Agent interface, Nemotron 3 Ultra 550B A55B +25: 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.); Nemotron 3 Ultra 550B A55B 90 (The chat template earns 20, a Jinja file in the repository.)
- Documentation and upkeep, Nemotron 3 Ultra 550B A55B +24: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Nemotron 3 Ultra 550B A55B 70 (The model card earns 20, all seven items with limitations in the linked subcard.)
- Risk, Nemotron 3 Ultra 550B A55B +10: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Nemotron 3 Ultra 550B A55B 70 (File safety earns 15, safetensors only but with 10 off because the documented commands pass trust-remote-code and the repository ships Python files.)