Liquid AI
LFM 2.5 MoE IQ2_M 8B-A1B
Smallest LFM MoE download, with more loss of answer quality. Experimental reasoning model; stores all 8B weights and activates about 1B per token.
About LFM 2.5 MoE IQ2_M 8B-A1B
Smallest LFM MoE download, with more loss of answer quality. Experimental reasoning model; stores all 8B weights and activates about 1B per token.
Every model in this catalog runs locally in the Offline AI Chat app. After the download finishes, LFM 2.5 MoE IQ2_M answers on your phone with no connection, and your prompts and replies are never uploaded.
- Download size
- 2.8 GB (UD-IQ2_M GGUF)
- Memory needed
- 6 GB minimum · 8 GB recommended
- Context in app
- 4,096 tokens
- Runs on
- Android 8+, 64-bit · iOS in private testing
- Access
- Offline Plus subscription
- License
- LFM Open License v1.0
- Model source
- Liquid AI on Hugging Face