noctrex/LFM2.5-2.6B-heretic-uncensored-GGUF overview
These are quantizations of the model LiquidAI / LFM2.5 2.6B https://huggingface.co/LiquidAI/LFM2.5 2.6B . Abliterated with heretic 1.4.0 The quantizations were…
Runs locally from ~2.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-2.6B-heretic-uncensored-BF16.gguf | GGUF | BF16 | 5.03 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-F16.gguf | GGUF | F16 | 5.03 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-IQ4_NL.gguf | GGUF | IQ4_NL | 1.48 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-IQ4_XS.gguf | GGUF | IQ4_XS | 1.41 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-Q4_K_M.gguf | GGUF | Q4_K_M | 1.56 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-Q5_K_M.gguf | GGUF | Q5_K_M | 1.81 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-Q6_K.gguf | GGUF | Q6_K | 2.07 GB | Download |
| LFM2.5-2.6B-heretic-uncensored-Q8_0.gguf | GGUF | Q8_0 | 2.68 GB | Download |
| imatrix.gguf | GGUF | GGUF | 2.3 MB | Download |
Model Details
| Model ID | noctrex/LFM2.5-2.6B-heretic-uncensored-GGUF |
|---|---|
| Author | noctrex |
| Pipeline | text-generation |
| License | — |
| Base model | LiquidAI/LFM2.5-2.6B |
| Last modified | 2026-08-04T22:52:34.000Z |
Model README
---
pipeline_tag: text-generation
base_model:
- LiquidAI/LFM2.5-2.6B
tags:
- heretic
- uncensored
- abliterated
---
These are quantizations of the model LiquidAI / LFM2.5-2.6B.
Abliterated with heretic 1.4.0
The quantizations were created using an imatrix merged from combined\_en\_medium and harmful.txt to leverage the abliterated nature of the model.
| Metric | This model | Original model |
| :----- | :--------: | :---------------------------: |
| Refusals | 7/100 | 96/100 |
| KL divergence | 0.0146 | 0 |
Run noctrex/LFM2.5-2.6B-heretic-uncensored-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models