# LFM2.5-2.6B vs LFM3-1.7B (slim)

> LFM3-1.7B scores 61 (C) to LFM2.5-2.6B's 50.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-1-7b.md (~9,300 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-1-7b.json · canonical https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-1-7b
- 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 LFM2.5-2.6B's 50.3 (D), and leads in 2 of 4 scored categories. LFM2.5-2.6B leads on reach and risk. Both do open-weight models you run yourself.

- LFM2.5-2.6B: D 50.3, rank #146 of 160 open-weight models · https://www.anchorterminal.com/tools/lfm2-5-2-6b.min.md
- LFM3-1.7B: C 61, rank #69 of 160 open-weight models · https://www.anchorterminal.com/tools/lfm3-1-7b.min.md
- LFM2.5-2.6B, good for Agents that want a small local helper for tool calls, extraction and RAG on a laptop, phone or CPU, at organisations under the licence's revenue threshold Ahead on Reach, 90 against 85; Risk, 50 against 40.
- 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 Agent interface, 100 against 75; Documentation and upkeep, 67 against 57.

| Category | LFM2.5-2.6B | LFM3-1.7B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 85 |
| Risk (20%) | 50 | 40 |
| Agent interface (10%) | 75 | 100 |
| Documentation and upkeep (10%) | 57 | 67 |

| Fact (where they differ) | LFM2.5-2.6B | LFM3-1.7B |
| --- | --- | --- |
| Last release | 2026-11-03 | 2026-11-09 |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Agent interface, LFM3-1.7B +25: LFM2.5-2.6B 75 (The chat template earns 20 for chat_template.jinja in the repository.); 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.)
- Risk, LFM2.5-2.6B +10: LFM2.5-2.6B 50 (File safety earns 25, safetensors and GGUF only, and nothing from the repository runs to load it or build prompts.); LFM3-1.7B 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).)
- Documentation and upkeep, LFM3-1.7B +10: LFM2.5-2.6B 57 (The model card earns 17, with everything but a knowledge cut-off.); 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…)
- Reach, LFM2.5-2.6B +5: LFM2.5-2.6B 90 (Memory earns the full 30, since Liquid's own 4-bit GGUF is 1.59 GB and fits 8 GB with room to spare.); 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.)