LFM2 24B A2B is an open-source language model by LiquidAI. Features: 24b LLM, VRAM: 47.7GB, Context: 125K, License: other.
Arxiv:2511.23404 Ar Conversational De Edge En Endpoints compatible Es Fr Ja Ko Lfm2 Lfm2 moe Liquid Pt Region:us Safetensors Zh
Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2-24B-A2B
LFM2 24B A2B Parameters and Internals
| LLM Name | LFM2 24B A2B |
| Repository 🤗 | https://huggingface.co/LiquidAI/LFM2-24B-A2B |
| Model Size | 24b |
| Required VRAM | 47.7 GB |
| Updated | 2026-04-01 |
| Maintainer | LiquidAI |
| Model Type | lfm2_moe |
| Model Files | |
| Supported Languages | en ar zh fr de ja ko es pt |
| Model Architecture | Lfm2MoeForCausalLM |
| License | other |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 5.0.0rc1 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|pad|> |
| Vocabulary Size | 65536 |
Rank the LFM2 24B A2B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52394 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a