license: other
license_name: lfm1.0
license_link: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B/blob/main/LICENSE
base_model: pottokao/LFM2.5-24B-A2B-Uncensored
pipeline_tag: text-generation
tags:
- liquid
- lfm2.5
- moe
- uncensored
- heretic
- ara
- gguf
- llama.cpp
LFM2.5-24B-A2B-Uncensored-GGUF
GGUF quantizations of pottokao/LFM2.5-24B-A2B-Uncensored
(LiquidAI LFM2.5-24B-A2B decensored with Heretic ARA; refusals 89/100 → 0/100, KL 0.260 on the BF16 weights).
| File | Size | Notes |
|---|---|---|
LFM2.5-24B-A2B-Uncensored-Q4_K_M.gguf |
14.5 GB | no imatrix |
LFM2.5-24B-A2B-Uncensored-IQ4_XS.gguf |
— | imatrix |
LFM2.5-24B-A2B-Uncensored-IQ3_M.gguf |
— | imatrix, fits a single 16 GB GPU comfortably |
- All files keep every
attn_outputtensor at Q8_0 (--tensor-type attn_output=q8_0): the decensoring edit
lives inblk.38.attn_output, and the 10 attention outputs together are only ~40M parameters. - imatrix computed on the decensored BF16 GGUF with
bartowski's calibration_datav3. - Converted and quantized with llama.cpp
0a1ef30.
KV cache is small (only 10 of 40 layers are attention, ~20 KB per token in F16), so most of the VRAM goes to weights.
llama-server -m LFM2.5-24B-A2B-Uncensored-IQ3_M.gguf -ngl 99 -c 32768 --jinja \
--temp 0.1 --top-k 50 --repeat-penalty 1.05
The model always thinks before answering; allow a generous output budget. Liquid AI's official
DSpark draft targets the original weights (acceptance on
this model not yet measured).
⚠️ Notice
Refusal behavior has been substantially reduced. Intended for research, red-teaming and personal use; you are
responsible for your use and for complying with laws and the base model license.
License & credits
Derivative of LiquidAI/LFM2.5-24B-A2B under the LFM Open License
v1.0. Decensoring with Heretic (p-e-w, AGPL-3.0) / ARA. Quantized with llama.cpp.