# Devstral Small 2 vs Qwen3-Omni-30B-A3B-Instruct (slim)

> Devstral Small 2 scores 61 (C) to Qwen3-Omni-30B-A3B-Instruct's 41.8 (E) 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-qwen3-omni-30b-a3b-instruct.md (~10,950 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct
- 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 scores 61 (C) on agent readiness against Qwen3-Omni-30B-A3B-Instruct's 41.8 (E), and leads in every scored category. 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
- Qwen3-Omni-30B-A3B-Instruct: E 41.8, rank #158 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-omni-30b-a3b-instruct.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; Risk, 60 against 55; Agent interface, 65 against 60; Documentation and upkeep, 46 against 26.
- Qwen3-Omni-30B-A3B-Instruct, good for Agents on a machine with about 96 GB to spare that need one local model to hear, see and answer by voice

| Category | Devstral Small 2 | Qwen3-Omni-30B-A3B-Instruct |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 55 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 60 |
| Documentation and upkeep (10%) | 46 | 26 |

| Fact (where they differ) | Devstral Small 2 | Qwen3-Omni-30B-A3B-Instruct |
| --- | --- | --- |
| Vendor | Mistral AI | Alibaba (Qwen team) |
| Last release | 2026-07-15 | 2025-09-22 |
| Agent reviews | none | 2/5 (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.); Qwen3-Omni-30B-A3B-Instruct 55 (Memory earns 10, because the only build is the 70.5 GB BF16 checkpoint, about 85 GB with a fifth added, which fits only the reference machine's band.)
- Documentation and upkeep, Devstral Small 2 +20: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Qwen3-Omni-30B-A3B-Instruct 26 (Model card 11, intended use, architecture, parameters and languages are there, limitations, context and a cut-off aren't.)
- Risk, Devstral Small 2 +5: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Qwen3-Omni-30B-A3B-Instruct 55 (File safety 25, safetensors only and no code in the repository, so the cookbook's trust_remote_code flag runs nothing.)
- Agent interface, Devstral Small 2 +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.); Qwen3-Omni-30B-A3B-Instruct 60 (Chat template 20, a Jinja file in the repository.)