Instructions to use prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-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 prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF: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 prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF: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 prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16

Use Docker

docker model run hf.co/prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16

LM Studio
Jan
Ollama
How to use prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16
```
Unsloth Desktop
Docker Model Runner
How to use prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16
```

Lemonade

How to use prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF:BF16

Run and chat with the model

lemonade run user.KAIROS-MM-Qwen2.5-VL-SFT-GGUF-BF16

List all available models

lemonade list

Atomic Chat

KAIROS-MM-Qwen2.5-VL-SFT-GGUF

KAIROS-MM-Qwen2.5-VL-7B-SFT is a multimodal reasoning model based on Qwen2.5-VL, designed to enable robots and vision AI agents to reason about the real world using physics understanding, prior knowledge, and common sense. The model understands space, time, and fundamental physical principles, and is well suited for planning, decision making, and long horizon video reasoning in embodied and agentic systems. It serves as a planning and reasoning backbone for embodied agents, allowing them to infer what actions to take next based on visual observations, temporal context, and physical constraints.

KAIROS-MM-Qwen2.5-VL-SFT [GGUF]

File Name	Quant Type	File Size	File Link
KAIROS-MM-Qwen2.5-VL-SFT.BF16.gguf	BF16	15.2 GB	Download
KAIROS-MM-Qwen2.5-VL-SFT.F16.gguf	F16	15.2 GB	Download
KAIROS-MM-Qwen2.5-VL-SFT.Q8_0.gguf	Q8_0	8.1 GB	Download
KAIROS-MM-Qwen2.5-VL-SFT.mmproj-bf16.gguf	mmproj-bf16	1.36 GB	Download
KAIROS-MM-Qwen2.5-VL-SFT.mmproj-f16.gguf	mmproj-f16	1.36 GB	Download
KAIROS-MM-Qwen2.5-VL-SFT.mmproj-q8_0.gguf	mmproj-q8_0	856 MB	Download