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.
- Approx. VRAM
- ~14–16 GB (Q4)
- License
- Other
- Downloads
- 1M / 30d
updated Oct 28, 2026
Search models, news, guides and FAQs.
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.
This repository ships GGUF files. Ollama can pull them from Hugging Face; adjust the quant tag if needed:
ollama run hf.co/AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF:Q4_K_MUses the Hugging Face CLI. Install it with pip install -U huggingface_hub if needed.
hf download AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUFIn LM Studio, search for the repository name and pick a GGUF quant that fits your VRAM. With llama.cpp, use llama-cli -hf AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF. See the setup guide for full flags and sampling defaults.
Listed quantizations: GGUF.
An uncensored MiniCPM-V 4.7 35B-A3B MoE build with a refusal-direction edit, distributed as GGUF for multimodal local use.
Method: abliteration. License: Apache-2.0. 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.
LiquidAI/LFM2.5-24B-A2B
An uncensored LFM2.5 24B-A2B MoE build using a refusal-direction edit, distributed as GGUF for llama.cpp.
updated Oct 28, 2026