Instructions to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-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 huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL
# Run inference directly in the terminal:
llama cli -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL
# Run inference directly in the terminal:
llama cli -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

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 huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL
# Run inference directly in the terminal:
./llama-cli -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

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 huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Use Docker

docker model run hf.co/huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

LM Studio
Jan

vLLM

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

SGLang

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with Ollama:
```
ollama run hf.co/huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL
```

Unsloth Studio

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-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 huihui-ai/Huihui-Kimi-K2.6-abliterated-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 huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF to start chatting

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL
```

Lemonade

How to use huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull huihui-ai/Huihui-Kimi-K2.6-abliterated-GGUF:UD-Q2_K_XL

Run and chat with the model

lemonade run user.Huihui-Kimi-K2.6-abliterated-GGUF-UD-Q2_K_XL

List all available models

lemonade list

建议出Q4_K_M及以上量化的

by sndnnlfhvk - opened 14 days ago

Discussion

sndnnlfhvk

14 days ago

Q4_K_M 是“甜点位”，大模型量化有一个明显的边际效应，模型的智商损耗曲线是非常平缓的。
然而，一旦低于 4 位（比如到 Q3 或 Q2），模型的智商会发生“断崖式”下跌。Q4 恰好站在了悬崖边上——它拿到了最大的瘦身红利，同时又勉强保住了核心智商。
Q3_K / Q2_K量化智商损耗极高 (模型开始胡言乱语)，纯粹为了“跑得动”。
忽略掉用户"本地"是否跑的动的问题，现在很多云服务提供商支持从huggingface拉取模型，作者你的模型一些平台几乎都有，现在就需要智商损耗低的abliterated模型。

shibuzhang

14 days ago

•

edited 14 days ago

Kimi k2.6 is a very solid base model, and Unsloth's dynamic quantization for Q2K is actually quite high quality. Huihui's ablated version is also impressive—it completely eliminates the "alignment tax," and even with tens of thousands of tokens in context, it doesn't start talking nonsense.

That said, having used Unsloth's non-abliterated Q3K versions, I can see there is still a noticeable gap between Q2K and Q3K. I’d honestly love to get my hands on an abliterated Q3K version of Kimi k2.6; since Kimi k3 is massive (around 2800B), k2.6 might be the "swan song" for running Kimi models locally. I've also noticed that K2.7's creative writing has declined。