# Devstral Small 2 vs MiMo-V2.6 Distill Qwen 9B (slim)

> Devstral Small 2 and MiMo-V2.6 Distill Qwen 9B score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b.md (~10,400 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b
- 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 MiMo-V2.6 Distill Qwen 9B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiMo-V2.6 Distill Qwen 9B leads on risk and agent interface. 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
- MiMo-V2.6 Distill Qwen 9B: C 61, rank #47 of 160 open-weight models · https://www.anchorterminal.com/tools/mimo-v2-6-distill-qwen-9b.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; Documentation and upkeep, 46 against 40.
- MiMo-V2.6 Distill Qwen 9B, good for Researchers and agents that want a small coding and terminal-agent model to fine-tune further on a 24 GB GPU, or to run at 4-bit through Ollama in about 8 GB. Ahead on Risk, 65 against 60; Agent interface, 70 against 65.

| Category | Devstral Small 2 | MiMo-V2.6 Distill Qwen 9B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 80 |
| Risk (20%) | 60 | 65 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 46 | 40 |

| Fact (where they differ) | Devstral Small 2 | MiMo-V2.6 Distill Qwen 9B |
| --- | --- | --- |
| Vendor | Mistral AI | Xiaomi (MiMo team) |
| Licence | Apache-2.0 | MIT (metadata only, no LICENSE file); built on Qwen3.5-9B under Apache 2.0 |
| Last release | 2026-07-15 | 2026-09-21 |
| Agent reviews | none | 2.3/5 (4) |

Why the edge:
- 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.); MiMo-V2.6 Distill Qwen 9B 80 (Memory 30 of 30, Ollama's library build at q4_K_M is 6.6 GB, 7.9 GB with a fifth added, while Xiaomi's only build is BF16 at 18.85 GB.)
- Documentation and upkeep, Devstral Small 2 +6: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); MiMo-V2.6 Distill Qwen 9B 40 (Model card 5 of 20, intended use and parameters only.)
- Risk, MiMo-V2.6 Distill Qwen 9B +5: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); MiMo-V2.6 Distill Qwen 9B 65 (File safety 25, safetensors only and no repository code runs.)
- Agent interface, MiMo-V2.6 Distill Qwen 9B +5: 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.); MiMo-V2.6 Distill Qwen 9B 70 (Chat template 20, a Jinja file in the repository.)