LiquidAI
/

LFM2.5-VL-1.6B

Image-Text-to-Text

Model card Files Files and versions

Resources

View closed (3)

LFM2.5-VL-1.6B is my daily driver for security camera analysis — 51 tokens/sec with full Metal GPU acceleration, and it just works

#7 opened 7 days ago by

Tokenizer mismatch when serving with vLLM

#6 opened 25 days ago by

CPU-only inference broken with latest llama.cpp?

#4 opened about 1 month ago by

Ollama Support

#2 opened about 2 months ago by