eriktonon/ lfm2.5-uncensored

39 yesterday

Liquid AI LFM 2.5 24B-A2B Uncensored Hybrid MoE (24B total, 2B active, Q4_K_M + GGUF <think> patch). 330.6 tok/s Peak Decode, 9,030 tok/s Prefill, 0.0% Hallucination (6/6), 100% Zero-Refusal. License: LFM Open v1.0 / Apache-2.0.

24b

3 models

lfm2.5-uncensored:latest
7755bbf1988b • 15GB • 128K context window •
Text input • 2 days ago
lfm2.5-uncensored:24b latest
7755bbf1988b • 15GB • 128K context window •
Text input • yesterday
lfm2.5-uncensored:24b-a2b
7755bbf1988b • 15GB • 128K context window •
Text input • 2 days ago