Instructions to use mradermacher/LFM2-VL-1.6B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mradermacher/LFM2-VL-1.6B-GGUF with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mradermacher/LFM2-VL-1.6B-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use mradermacher/LFM2-VL-1.6B-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use mradermacher/LFM2-VL-1.6B-GGUF with Ollama:
ollama run hf.co/mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use mradermacher/LFM2-VL-1.6B-GGUF with Docker Model Runner:
docker model run hf.co/mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
- Lemonade
How to use mradermacher/LFM2-VL-1.6B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mradermacher/LFM2-VL-1.6B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.LFM2-VL-1.6B-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -46,12 +46,14 @@ more details, including on how to concatenate multi-part files.
|
|
| 46 |
|:-----|:-----|--------:|:------|
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q2_K.gguf) | Q2_K | 0.6 | |
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
|
|
|
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality |
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q3_K_L.gguf) | Q3_K_L | 0.7 | |
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.IQ4_XS.gguf) | IQ4_XS | 0.8 | |
|
| 52 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended |
|
| 53 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended |
|
| 54 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q5_K_S.gguf) | Q5_K_S | 0.9 | |
|
|
|
|
| 55 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q5_K_M.gguf) | Q5_K_M | 0.9 | |
|
| 56 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
|
| 57 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality |
|
|
|
|
| 46 |
|:-----|:-----|--------:|:------|
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q2_K.gguf) | Q2_K | 0.6 | |
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement |
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality |
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q3_K_L.gguf) | Q3_K_L | 0.7 | |
|
| 52 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.IQ4_XS.gguf) | IQ4_XS | 0.8 | |
|
| 53 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended |
|
| 54 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended |
|
| 55 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q5_K_S.gguf) | Q5_K_S | 0.9 | |
|
| 56 |
+
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement |
|
| 57 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q5_K_M.gguf) | Q5_K_M | 0.9 | |
|
| 58 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
|
| 59 |
| [GGUF](https://huggingface.co/mradermacher/LFM2-VL-1.6B-GGUF/resolve/main/LFM2-VL-1.6B.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality |
|