LFM3-VL-2B: hardware requirements
LFM3-VL-2B needs about 1.8 GB of memory at Q4_K_M quantization: a 1.1 GB download plus room for context and a runtime allowance. That fits a machine with 8GB RAM.
Parameters
1.9B
Tier
Runs on a laptop
Licence
See model card
Released
2026-10-23
Will it run on your machine?
8GB RAMRuns well16GB RAMRuns well24GB RAMRuns well32GB RAMRuns well64GB RAMRuns well128GB RAMRuns well8GB VRAMRuns well12GB VRAMRuns well16GB VRAMRuns well24GB VRAMRuns well32GB VRAMRuns well
Download sizes by quantization
Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?
| Quant | Download | RAM @ 4K | RAM @ 32K | Source |
|---|---|---|---|---|
| Q4_K_Mrecommended | 1.1 GB | 1.8 GB | 3.2 GB | LiquidAI/LFM3-VL-2B-GGUF |
| Q5_K_M | 1.3 GB | 2.0 GB | 3.4 GB | LiquidAI/LFM3-VL-2B-GGUF |
| Q6_K | 1.4 GB | 2.2 GB | 3.6 GB | LiquidAI/LFM3-VL-2B-GGUF |
| Q8_0 | 2.0 GB | 2.8 GB | 4.2 GB | LiquidAI/LFM3-VL-2B-GGUF |
| BF16 | 3.8 GB | 4.6 GB | 6.0 GB | LiquidAI/LFM3-VL-2B-GGUF |
Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).
Other sizes of LFM3
Model card on HuggingFace →API specs & pricing →Verified 2026-10-28Listed for 120 days after release