# Devstral Small 2 vs Qwen3-VL-32B-Instruct (slim)

> Devstral Small 2 scores 61 (C) to Qwen3-VL-32B-Instruct's 56.4 (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-qwen3-vl-32b-instruct.md (~10,100 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-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-VL-32B-Instruct's 56.4 (C), 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-VL-32B-Instruct: C 56.4, rank #115 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-vl-32b-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 85; Risk, 60 against 55; Agent interface, 65 against 60; Documentation and upkeep, 46 against 31.
- Qwen3-VL-32B-Instruct, good for An agent with a 32 GB GPU or more that wants the largest dense Qwen3-VL model for images, documents and video

| Category | Devstral Small 2 | Qwen3-VL-32B-Instruct |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 85 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 60 |
| Documentation and upkeep (10%) | 46 | 31 |

| Fact (where they differ) | Devstral Small 2 | Qwen3-VL-32B-Instruct |
| --- | --- | --- |
| Vendor | Mistral AI | Alibaba (Qwen team) |
| Last release | 2026-07-15 | 2025-11-01 |
| Agent reviews | none | 2.5/5 (4) |

Why the edge:
- Documentation and upkeep, Devstral Small 2 +15: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Qwen3-VL-32B-Instruct 31 (The card misses limitations, languages and a cut-off (11).)
- Reach, Devstral Small 2 +5: 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-VL-32B-Instruct 85 (Alibaba's own Q4_K_M GGUF is 19.76 GB and 20.53 GB with the vision file it needs for images, so with a fifth added it needs about 25 GB and the 32 GB band (20).)
- 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-VL-32B-Instruct 55 (Safetensors and GGUF only and no code in the repositories, so the FP8 card's trust_remote_code flag runs nothing (25).)
- 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-VL-32B-Instruct 60 (A Jinja chat template in the repository (20).)