# LFM3-VL-2B: RAM and VRAM requirements

> LFM3-VL-2B is a 1.92B LFM model. At Q4_K_M it needs about **2.5 GB** to run and fits **49 of 49** tracked devices. Minimum to run: Nvidia GeForce RTX 2060 (6GB).

Catalog updated: 2026-11-01. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 1.38 GB | ~2.5 GB |
| Q8_0 | 2.07 GB | ~3.2 GB |
| FP16 | 3.58 GB | ~4.7 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Nvidia GeForce RTX 2060 (6GB)** (6 GB): Yes, it runs (room for FP16)
- **iPhone 17** (8 GB): Yes, it runs (room for Q8_0)
- **iPhone 17 Pro** (12 GB): Yes, it runs (room for FP16)
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): Yes, it runs (room for FP16)
- **Samsung Galaxy S26 Ultra (16GB, 1TB config)** (16 GB): Yes, it runs (room for FP16)
- **Apple M4 Pro (24GB)** (24 GB): Yes, it runs (room for FP16)
- **Apple M4 Pro (48GB)** (48 GB): Yes, it runs (room for FP16)
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs (room for FP16)

Full table of all 49 devices: https://localmodel.run/model/lfm3-vl-2b

## How to run
Quickest path: `ollama run lfm3-vl:2b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 1.92B
- Default context: 125k tokens
- License: LFM Open License v1.0 (commercial use: conditional)
- Released: 2026-10
- HuggingFace: 9,121 downloads/mo, 195 likes

## FAQ
### How much VRAM or RAM does LFM3-VL-2B need?
About 2.5 GB at Q4_K_M (weights 1.38 GB + KV cache + overhead) at a 4k context. Budget ~3.2 GB for Q8_0.
### Can LFM3-VL-2B run on a laptop?
Yes. LFM3-VL-2B fits on a 16 GB laptop or Mac at Q4_K_M, and runs on Apple Silicon or a 12 GB+ GPU comfortably.
### Can I use LFM3-VL-2B commercially?
Conditionally: LFM Open License v1.0: free for organizations below $10M annual revenue; larger organizations require separate terms..

Sources: https://huggingface.co/LiquidAI/LFM3-VL-2B, https://huggingface.co/LiquidAI/LFM3-VL-2B/blob/main/config.json, https://huggingface.co/LiquidAI/LFM3-VL-2B/blob/main/LICENSE, https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF, https://ollama.com/library/lfm3-vl:2b
More: https://localmodel.run/model/lfm3-vl-2b