Model Intelligence Sheet
konradjr007/LFM2.5-VL-450M-twinx-gguf overview
LFM2.5 VL 450M twinx gguf : GGUF This model was finetuned and converted to GGUF format using Unsloth https://github.com/unslothai/unsloth . Example usage : For…
Runs locally from ~168.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
9 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-VL-450M.BF16.gguf | GGUF | GGUF | 678.5 MB | Download |
| LFM2.5-VL-450M.F16-mmproj.gguf | GGUF | GGUF | 180.4 MB | Download |
| LFM2.5-VL-450M.F16.gguf | GGUF | GGUF | 678.5 MB | Download |
| LFM2.5-VL-450M.Q2_K_L.gguf | GGUF | GGUF | 168.7 MB | Download |
| LFM2.5-VL-450M.Q3_K_M.gguf | GGUF | GGUF | 184.2 MB | Download |
| LFM2.5-VL-450M.Q4_K_M.gguf | GGUF | GGUF | 218.7 MB | Download |
| LFM2.5-VL-450M.Q5_K_M.gguf | GGUF | GGUF | 248.3 MB | Download |
| LFM2.5-VL-450M.Q6_K.gguf | GGUF | GGUF | 279.8 MB | Download |
| LFM2.5-VL-450M.Q8_0.gguf | GGUF | GGUF | 361.7 MB | Download |
Model Details
| Model ID | konradjr007/LFM2.5-VL-450M-twinx-gguf |
|---|---|
| Author | konradjr007 |
| Pipeline | — |
| License | — |
| Base model | — |
| Last modified | 2026-06-19T17:42:44.000Z |
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
- vision-language-model
---
LFM2.5-VL-450M-twinx-gguf : GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
llama-cli -hf konradjr007/LFM2.5-VL-450M-twinx-gguf --jinja - For multimodal models:
llama-mtmd-cli -hf konradjr007/LFM2.5-VL-450M-twinx-gguf --jinja
Available Model files:
LFM2.5-VL-450M.BF16.ggufLFM2.5-VL-450M.F16-mmproj.gguf
This was trained 2x faster with Unsloth
Run konradjr007/LFM2.5-VL-450M-twinx-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models