Instructions to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("richardyoung/Kimi-VL-A3B-Thinking-GGUF", dtype="auto")

llama-cpp-python

How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="richardyoung/Kimi-VL-A3B-Thinking-GGUF",
	filename="Kimi-VL-A3B-Thinking-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf richardyoung/Kimi-VL-A3B-Thinking-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 richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf richardyoung/Kimi-VL-A3B-Thinking-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 richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M

Use Docker

docker model run hf.co/richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with Ollama:
```
ollama run hf.co/richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M
```

Unsloth Studio

How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for richardyoung/Kimi-VL-A3B-Thinking-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for richardyoung/Kimi-VL-A3B-Thinking-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for richardyoung/Kimi-VL-A3B-Thinking-GGUF to start chatting

Docker Model Runner
How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with Docker Model Runner:
```
docker model run hf.co/richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M
```

Lemonade

How to use richardyoung/Kimi-VL-A3B-Thinking-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull richardyoung/Kimi-VL-A3B-Thinking-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Kimi-VL-A3B-Thinking-GGUF-Q4_K_M

List all available models

lemonade list

Kimi-VL-A3B-Thinking GGUF

GGUF quantizations of moonshotai/Kimi-VL-A3B-Thinking-2506 for use with llama.cpp and Ollama.

Model Description

Kimi-VL-A3B-Thinking is a powerful vision-language model with extended thinking capabilities from Moonshot AI. It features a Mixture of Experts (MoE) architecture built on DeepSeek2 for efficient inference with strong reasoning capabilities.

Key Features

Vision & Reasoning - Understands images and uses chain-of-thought reasoning
128K Context - Massive 131,072 token context window
MoE Architecture - 64 experts + 2 shared experts for efficient inference
DeepSeek2 Base - Built on proven DeepSeek2 architecture with MLA attention

Available Quantizations

Filename	Quant	Size	Description
Kimi-VL-A3B-Thinking-Q4_K_M.gguf	Q4_K_M	9.8 GB	Best balance of quality and speed (recommended)
Kimi-VL-A3B-Thinking.gguf	F16	30 GB	Full precision

Usage

With Ollama

# Pull and run (Q4_K_M by default)
ollama run richardyoung/kimi-vl-a3b-thinking

# Or specific quantization
ollama run richardyoung/kimi-vl-a3b-thinking:f16

With llama.cpp

# Download a quantization
wget https://huggingface.co/richardyoung/Kimi-VL-A3B-Thinking-GGUF/resolve/main/Kimi-VL-A3B-Thinking-Q4_K_M.gguf

# Run with llama.cpp
./llama-cli -m Kimi-VL-A3B-Thinking-Q4_K_M.gguf -p "Analyze this image step by step:" --image your_image.jpg

Technical Requirements

Minimum: 16GB RAM
Recommended: 32GB RAM or Apple Silicon Mac with 24GB+ unified memory

Chat Template

Kimi-VL uses a custom template format:

<|im_system|>system<|im_middle|>{system_message}<|im_end|>
<|im_user|>user<|im_middle|>{user_message}<|im_end|>
<|im_assistant|>assistant<|im_middle|>{assistant_response}<|im_end|>

Credits

Original Model: Moonshot AI
Quantization: Richard Young (deepneuro.ai)

License

MIT License

Downloads last month: 182

GGUF

Model size

16B params

Architecture

deepseek2

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for richardyoung/Kimi-VL-A3B-Thinking-GGUF

Base model

moonshotai/Moonlight-16B-A3B

Finetuned

moonshotai/Kimi-VL-A3B-Instruct

Finetuned

moonshotai/Kimi-VL-A3B-Thinking-2506

Quantized

(11)

this model

richardyoung
/

Kimi-VL-A3B-Thinking-GGUF