# LFM3-Omni-2B vs MiniCPM-o 4.5 (slim)

> LFM3-Omni-2B and MiniCPM-o 4.5 score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/lfm3-omni-2b-vs-minicpm-o-4-5.md (~9,000 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/lfm3-omni-2b-vs-minicpm-o-4-5.json · canonical https://www.anchorterminal.com/compare/lfm3-omni-2b-vs-minicpm-o-4-5
- 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-Omni-2B and MiniCPM-o 4.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-o 4.5 leads on reach and documentation and upkeep. Both do open-weight models you run yourself.

- LFM3-Omni-2B: C 61, rank #71 of 160 open-weight models · https://www.anchorterminal.com/tools/lfm3-omni-2b.min.md
- MiniCPM-o 4.5: C 61, rank #48 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-o-4-5.min.md
- LFM3-Omni-2B, good for Voice and camera agents on a laptop or phone that want one small model for hearing, seeing, speaking and calling tools Ahead on Agent interface, 70 against 35.
- MiniCPM-o 4.5, good for Agents that need a local model to see, hear and speak on a laptop or a single small GPU, with a plain licence. Ahead on Reach, 90 against 80; Documentation and upkeep, 66 against 49.

| Category | LFM3-Omni-2B | MiniCPM-o 4.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 80 | 90 |
| Risk (20%) | 40 | 40 |
| Agent interface (10%) | 70 | 35 |
| Documentation and upkeep (10%) | 49 | 66 |

| Fact (where they differ) | LFM3-Omni-2B | MiniCPM-o 4.5 |
| --- | --- | --- |
| Vendor | Liquid AI | OpenBMB |
| Licence | LFM Open License v1.0 (free commercial use below $10M annual revenue) | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards |
| llms.txt | yes | no |
| Last release | 2026-11-03 | 2026-10-24 |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Agent interface, LFM3-Omni-2B +35: LFM3-Omni-2B 70 (Chat template 20, chat_template.jinja in the repository (13,513 characters), with roles, images, video and audio, tools, deferred tools and tool results.); MiniCPM-o 4.5 35 (Chat template 20, a Jinja template in the tokenizer config.)
- Documentation and upkeep, MiniCPM-o 4.5 +17: LFM3-Omni-2B 49 (Model card 14, Intended use (one on-device model in place of separate speech recognition, vision, language and speech models), architecture, parameters (2.17B)…); MiniCPM-o 4.5 66 (Model card 11 of 20, limitations, context length and a knowledge cut-off are missing.)
- Reach, MiniCPM-o 4.5 +10: LFM3-Omni-2B 80 (Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB with its 0.29 GB projector file, and 1.39 GB × 1.2 = 1.7 GB, which fits 8 GB, well inside the 16 GB line.); MiniCPM-o 4.5 90 (Memory 30, OpenBMB's 4-bit GGUF with its vision file is 5.9 GB, about 7 GB with a fifth added.)