API Try Docs Blog

LFM3-VL-2B-NVFP4

NVFP4 version of LFM3-VL-2B for GPU inference.

Language feed-forward weights and activations use NVFP4 (W4A4, 16-value blocks). Attention, convolutions, embeddings, the output head and norms stay in BF16. The vision encoder and projector also stay in BF16. Sliding-window and RoPE settings are unchanged.

Find architecture and usage details in the original model card.

Use with SGLang

---

Support for LFM3-VL in SGLang is in review in sgl-project/sglang#46858. We will update this card when a release supports it.

python -m sglang.launch_server \
  --model-path LiquidAI/LFM3-VL-2B-NVFP4 \
  --reasoning-parser auto \
  --tool-call-parser auto