LFM2.5 2.6B

LiquidAI/LFM2.5-2.6B-GGUF:Q8_0

llama.cpp1 build benchmarkedbest build liquidai · Q8_013.8 GB84 tok/s

best build

Scores at a glance

measured avg16

Tool Calling180/27

Reasoning & Math144/28

0255075100

0–100 per task · n/m = cases passed (scores credit partial passes) · measured average covers 2/9 suite tasks

best build

config

deployment

run this buildllama.cpp

llama-server -hf LiquidAI/LFM2.5-2.6B-GGUF:Q8_0 -c 128000

Pulls the GGUF from Hugging Face and serves an OpenAI-compatible endpoint on :8080.

record

per-test results

Per-test scores, full transcripts, and the reproduce recipe.