Skip to content

Search wahloon.net

Search models, news, guides and FAQs.

Model catalog
Other24B-A2BAbliteration~14–16 GB (Q4)

LFM2.5-24B-A2B-Uncensored

LiquidAI/LFM2.5-24B-A2B

An uncensored LFM2.5 24B-A2B MoE build using a refusal-direction edit, distributed as GGUF for llama.cpp.

Run it

Ollama

This repository ships GGUF files. Ollama can pull them from Hugging Face; adjust the quant tag if needed:

ollama run hf.co/AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF:Q4_K_M

Download the weights

Uses the Hugging Face CLI. Install it with pip install -U huggingface_hub if needed.

hf download AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF

LM Studio / llama.cpp

In LM Studio, search for the repository name and pick a GGUF quant that fits your VRAM. With llama.cpp, use llama-cli -hf AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF. See the setup guide for full flags and sampling defaults.

Formats & tags

GGUF

Listed quantizations: GGUF.

#lfm#24b-a2b#moe#uncensored#abliterated#gguf

Notes

An uncensored LFM2.5 24B-A2B MoE build using a refusal-direction edit, distributed as GGUF for llama.cpp.

Method: abliteration. License: Other. Last catalog update: Oct 28, 2026. This entry links to a third-party repository; wahloon.net is not affiliated with the publisher. Verify the current model card, license and file list before downloading. You are responsible for how you use the model.

Browse all
Other35B-A3B
Abliteration

MiniCPM-V-4.7-35B-A3B-Uncensored

openbmb/MiniCPM-V-4.7-35B-A3B

An uncensored MiniCPM-V 4.7 35B-A3B MoE build with a refusal-direction edit, distributed as GGUF for multimodal local use.

Approx. VRAM
~21–22 GB (Q4)
License
Apache-2.0
Downloads
547.6K / 30d
#minicpm#35b-a3b#moe#uncensored

updated Oct 28, 2026