Instructions to use musk12/fastvlm-qwen2-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use musk12/fastvlm-qwen2-bf16 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 musk12/fastvlm-qwen2-bf16:BF16
# Run inference directly in the terminal:
llama cli -hf musk12/fastvlm-qwen2-bf16:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf musk12/fastvlm-qwen2-bf16:BF16
# Run inference directly in the terminal:
llama cli -hf musk12/fastvlm-qwen2-bf16:BF16

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 musk12/fastvlm-qwen2-bf16:BF16
# Run inference directly in the terminal:
./llama-cli -hf musk12/fastvlm-qwen2-bf16:BF16

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 musk12/fastvlm-qwen2-bf16:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf musk12/fastvlm-qwen2-bf16:BF16

Use Docker

docker model run hf.co/musk12/fastvlm-qwen2-bf16:BF16

LM Studio
Jan

vLLM

How to use musk12/fastvlm-qwen2-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "musk12/fastvlm-qwen2-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "musk12/fastvlm-qwen2-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/musk12/fastvlm-qwen2-bf16:BF16

Ollama
How to use musk12/fastvlm-qwen2-bf16 with Ollama:
```
ollama run hf.co/musk12/fastvlm-qwen2-bf16:BF16
```
Unsloth Desktop
Docker Model Runner
How to use musk12/fastvlm-qwen2-bf16 with Docker Model Runner:
```
docker model run hf.co/musk12/fastvlm-qwen2-bf16:BF16
```

Lemonade

How to use musk12/fastvlm-qwen2-bf16 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull musk12/fastvlm-qwen2-bf16:BF16

Run and chat with the model

lemonade run user.fastvlm-qwen2-bf16-BF16

List all available models

lemonade list

Atomic Chat

FastVLM Qwen2 (BF16, GGUF)

A BF16 Qwen2 GGUF model for higher-quality FastVLM language decoding. This model provides improved numerical fidelity compared to aggressive quantization and is suitable for BF16-capable inference.

Model file

fastvlm_qwen2_bf16.gguf

Usage

Use this model for higher-quality multimodal reasoning when BF16 performance is available.

./llama-cli -m fastvlm_qwen2_bf16.gguf -p "Your prompt here"

Base models

Derived from:

Downloads last month: 21

GGUF

Model size

0.6B params

Architecture

qwen2

Hardware compatibility

16-bit

Model tree for musk12/fastvlm-qwen2-bf16

Base model

Qwen/Qwen2.5-0.5B

Quantized

(116)

this model