# LFM3-1.7B vs Qwen3.5-2B (slim)

> LFM3-1.7B scores 61 (C) to Qwen3.5-2B's 50.5 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-2b.md (~9,150 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-2b.json · canonical https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-2b
- 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)

LFM3-1.7B scores 61 (C) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 3 of 4 scored categories. Qwen3.5-2B leads on risk. Both do open-weight models you run yourself.

- LFM3-1.7B: C 61, rank #69 of 160 open-weight models · https://www.anchorterminal.com/tools/lfm3-1-7b.min.md
- Qwen3.5-2B: D 50.5, rank #144 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-5-2b.min.md
- LFM3-1.7B, good for Agents on a laptop, phone or small server that need tool calling and a long context from a model under 2 GB at 4 bits Ahead on Reach, 85 against 80; Agent interface, 100 against 60; Documentation and upkeep, 67 against 37.
- Qwen3.5-2B, good for Builders who want a cheap local helper or fine-tuning base for narrow tasks and image reading on a laptop, small GPU or CPU Ahead on Risk, 55 against 40.

| Category | LFM3-1.7B | Qwen3.5-2B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 80 |
| Risk (20%) | 40 | 55 |
| Agent interface (10%) | 100 | 60 |
| Documentation and upkeep (10%) | 67 | 37 |

| Fact (where they differ) | LFM3-1.7B | Qwen3.5-2B |
| --- | --- | --- |
| Vendor | Liquid AI | Alibaba (Qwen team) |
| Licence | LFM Open License v1.0 (free commercial use below $10M annual revenue) | Apache-2.0 |
| llms.txt | yes | no |
| Last release | 2026-11-09 | 2026-03-02 |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Agent interface, LFM3-1.7B +40: LFM3-1.7B 100 (Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, tools, deferred tools, tool results and the thinking switch.); Qwen3.5-2B 60 (The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20).)
- Documentation and upkeep, LFM3-1.7B +30: LFM3-1.7B 67 (Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), a limitation (not recommended for agentic coding or complex multi-ste…); Qwen3.5-2B 37 (The card covers six of the seven items, missing only a cut-off (17), because it states the intended uses and warns about thinking loops.)
- Risk, Qwen3.5-2B +15: LFM3-1.7B 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).); Qwen3.5-2B 55 (Safetensors only with no remote code gives file safety its 25, and files in the Qwen organisation the publisher's GitHub links to, each with a hash on the Hub…)
- Reach, LFM3-1.7B +5: LFM3-1.7B 85 (Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB, and 1.10 GB × 1.2 = 1.3 GB, which fits 8 GB, well inside the 16 GB line.); Qwen3.5-2B 80 (Memory earns the full 30, since LM Studio's Q4_K_M GGUF with its vision projector is 1.94 GB, about 2.3 GB with the fifth added (Ollama's Q4_K_M build was 1.9 G…)