Models / LFM2
LFM2 by LiquidAI
7 models (350M to 24B) · ↓ 101K downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
LFM2 350M
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-350M | vLLM | 710 MB | 3.3 GB | $0.10/h RTX 3060 |
LFM2 700M
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-700M | vLLM | 1.5 GB | 4.2 GB | $0.10/h RTX 3060 |
LFM2 1.2B
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-1.2B | vLLM | 2.3 GB | 5.1 GB | $0.10/h RTX 3060 |
| ToolLiquidAI/LFM2-1.2B-Tool | vLLM | 2.3 GB | 5.1 GB | $0.10/h RTX 3060 |
| ExtractLiquidAI/LFM2-1.2B-Extract | vLLM | 2.3 GB | 5.1 GB | $0.10/h RTX 3060 |
| RAGLiquidAI/LFM2-1.2B-RAG | vLLM | 2.3 GB | 5.1 GB | $0.10/h RTX 3060 |
LFM2 2.6B
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-2.6B | vLLM | 5.1 GB | 8.5 GB | $0.10/h RTX 3060 |
| TranscriptLiquidAI/LFM2-2.6B-Transcript | vLLM | 5.1 GB | 8.5 GB | $0.10/h RTX 3060 |
LFM2 2.6B
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-2.6B-Exp | vLLM | 5.1 GB | 8.5 GB | $0.10/h RTX 3060 |
LFM2 8B
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-8B-A1B | vLLM | 17 GB | 21.2 GB | $0.18/h 2x RTX 3060 |
LFM2 24B
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|
| OriginalLiquidAI/LFM2-24B-A2B | vLLM | 48 GB | 56 GB | $0.75/h 4x RTX 5060 Ti |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").