LiquidAI / text-generation updated 3 weeks ago

LFM2.5-230M-GGUF

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

Params
Context
Downloads 30d
586 K
Likes
104
Licence: other Not gated GGUF 10 languages View on Hugging Face ↗

Download history

daily snapshots · 28 days
597 K180 K
Aug 25Sep 3Sep 12Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
LFM2.5-230M-QAD-Q4_0.gguf Q4_0 0.1 GB 0.7 GB ✅ Runs comfortably
LFM2.5-230M-Q4_K_M.gguf Q4_K_M 0.2 GB 0.7 GB ✅ Runs comfortably
LFM2.5-230M-Q5_K_M.gguf Q5_K_M 0.2 GB 0.7 GB ✅ Runs comfortably
LFM2.5-230M-Q6_K.gguf Q6_K 0.2 GB 0.7 GB ✅ Runs comfortably
LFM2.5-230M-Q8_0.gguf Q8_0 0.2 GB 0.8 GB ✅ Runs comfortably
LFM2.5-230M-BF16.gguf GGUF 0.5 GB 1.0 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_0
$ ollama run lfm2-5-230m-gguf

# pin the quantization explicitly
$ ollama run lfm2-5-230m-gguf-q4_0
est. VRAM 0.7 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
other
First seen on the Hub
2026-06-11
Training datasets
undisclosed
Added to our catalog
2026-08-25
Compare with any text-generation model