FadedRedStar/LFM2.5-VL-1.6B-heretic-GGUF overview
LFM2.5 VL 1.6B heretic — GGUF NOTE This card is a work in progress. Full architecture details, abliteration parameters, and inference instructions will be adde…
Runs locally from ~556.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-VL-1.6B-heretic-Q4_K_M.gguf | GGUF | Q4_K_M | 697.0 MB | Download |
| LFM2.5-VL-1.6B-heretic-Q5_K_M.gguf | GGUF | Q5_K_M | 804.3 MB | Download |
| LFM2.5-VL-1.6B-heretic-Q8_0.gguf | GGUF | Q8_0 | 1.16 GB | Download |
| mmproj-LFM2.5-VL-1.6B-heretic-BF16.gguf | GGUF | BF16 | 816.1 MB | Download |
| mmproj-LFM2.5-VL-1.6B-heretic-Q8_0.gguf | GGUF | Q8_0 | 556.1 MB | Download |
Model Details
| Model ID | FadedRedStar/LFM2.5-VL-1.6B-heretic-GGUF |
|---|---|
| Author | FadedRedStar |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | coder3101/LFM2.5-VL-1.6B-heretic |
| Last modified | 2026-07-05T12:46:22.000Z |
Model README
---
base_model: coder3101/LFM2.5-VL-1.6B-heretic
base_model_relation: quantized
library_name: gguf
license: apache-2.0
language:
- multilingual
pipeline_tag: image-text-to-text
tags:
- gguf
- text-generation
- multimodal
- vision
- reasoning
- thinking
- agentic
- tool-use
- abliterated
- uncensored
- lfm2
- conversational
---
LFM2.5-VL-1.6B-heretic — GGUF
> [!NOTE]
> This card is a work in progress. Full architecture details, abliteration parameters, and inference instructions will be added shortly.
This repository hosts GGUF weights and the associated vision projection matrix for LFM2.5-VL-1.6B-heretic, quantized from the source floating-point tensors provided by coder3101/LFM2.5-VL-1.6B-heretic.
Repository Files
| Filename | Format | Size | llama.cpp Build | Description |
|---|---|---|---|---|
| LFM2.5-VL-1.6B-heretic-Q4_K_M.gguf | Q4_K_M | 731 MB | b9860 | Main model weights |
| LFM2.5-VL-1.6B-heretic-Q5_K_M.gguf | Q5_K_M | 843 MB | b9860 | Main model weights, higher fidelity |
| LFM2.5-VL-1.6B-heretic-Q8_0.gguf | Q8_0 | 1.25 GB | b9860 | Main model weights, near-lossless |
| mmproj-LFM2.5-VL-1.6B-heretic-BF16.gguf | BF16 | 856 MB | b9860 | Vision projector (full precision) |
| mmproj-LFM2.5-VL-1.6B-heretic-Q8_0.gguf | Q8_0 | 583 MB | b9870 | Vision projector (compact) |
Run FadedRedStar/LFM2.5-VL-1.6B-heretic-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models