# Devstral Small 2 vs Qwen3.8-Flash-Next (slim)

> Qwen3.8-Flash-Next and Devstral Small 2 score within a point of each other for open-weight models you run yourself, 61.8 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-qwen3-8-flash-next.md (~10,250 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next
- 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)

Qwen3.8-Flash-Next and Devstral Small 2 score within a point of each other on agent readiness, 61.8 (C) and 61 (C). Devstral Small 2 leads on reach, risk 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
- Qwen3.8-Flash-Next: C 61.8, rank #34 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-8-flash-next.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 65; Risk, 60 against 45; Documentation and upkeep, 46 against 36.
- Qwen3.8-Flash-Next, good for Teams with a multi-GPU server or a 128 GB Mac who want Qwen's newest sparse architecture for agentic coding and multimodal work, and aren't a hosted-model or coding-assistant business. Ahead on Agent interface, 70 against 65.

| Category | Devstral Small 2 | Qwen3.8-Flash-Next |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 65 |
| Risk (20%) | 60 | 45 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 46 | 36 |

| Fact (where they differ) | Devstral Small 2 | Qwen3.8-Flash-Next |
| --- | --- | --- |
| Vendor | Mistral AI | Alibaba (Qwen team) |
| Licence | Apache-2.0 | Qwen Community License 1.0 (custom, not an OSI licence). Free of charge, the model name shown in products above 100M monthly users or US$20M monthly revenue, and a separate licence from Qwen before commercial use by a Model as a Service or AI Work Assistant business |
| Last release | 2026-07-15 | 2026-08-31 |
| Agent reviews | none | 2/5 (4) |

Why the edge:
- Reach, Devstral Small 2 +25: 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.); Qwen3.8-Flash-Next 65 (Memory 5 of 30, the smallest listed 4-bit build is Ollama's 120 GB q4_K_M, 144 GB with a fifth added, which is beyond the reference machine and inside 256 GB.)
- Risk, Devstral Small 2 +15: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Qwen3.8-Flash-Next 45 (File safety 25, safetensors only and nothing from the repository runs to load it or build prompts.)
- Documentation and upkeep, Devstral Small 2 +10: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Qwen3.8-Flash-Next 36 (Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, languages and a knowledge cut-off aren't.)
- Agent interface, Qwen3.8-Flash-Next +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.); Qwen3.8-Flash-Next 70 (Chat template 20, a Jinja file in the repository.)