eriktonon/ lfm2.5-uncensored:24b

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
... /
params
6809a27ce2f1 ยท 164B
{
"num_ctx": 65536,
"repeat_penalty": 1.1,
"stop": [
"<|im_start|>",
"<|im_end|>",
"<|endoftext|>"
],
"temperature": 0.6,
"top_k": 40,
"top_p": 0.92
}