Instructions to use laichaoyi/MixupModels with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laichaoyi/MixupModels with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="laichaoyi/MixupModels",
	filename="text_encoders/anima/Qwen3-0.6B-Base.Q8.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use laichaoyi/MixupModels 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 laichaoyi/MixupModels:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf laichaoyi/MixupModels:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf laichaoyi/MixupModels:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf laichaoyi/MixupModels: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 laichaoyi/MixupModels:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf laichaoyi/MixupModels: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 laichaoyi/MixupModels:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf laichaoyi/MixupModels:Q4_K_M

Use Docker

docker model run hf.co/laichaoyi/MixupModels:Q4_K_M

LM Studio
Jan
Ollama
How to use laichaoyi/MixupModels with Ollama:
```
ollama run hf.co/laichaoyi/MixupModels:Q4_K_M
```

Unsloth Studio

How to use laichaoyi/MixupModels 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 laichaoyi/MixupModels 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 laichaoyi/MixupModels to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for laichaoyi/MixupModels to start chatting

How to use laichaoyi/MixupModels with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf laichaoyi/MixupModels:Q4_K_M

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": "laichaoyi/MixupModels:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use laichaoyi/MixupModels with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf laichaoyi/MixupModels:Q4_K_M

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 laichaoyi/MixupModels:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use laichaoyi/MixupModels with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf laichaoyi/MixupModels:Q4_K_M

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 "laichaoyi/MixupModels:Q4_K_M" \
  --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 laichaoyi/MixupModels with Docker Model Runner:
```
docker model run hf.co/laichaoyi/MixupModels:Q4_K_M
```

Lemonade

How to use laichaoyi/MixupModels with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull laichaoyi/MixupModels:Q4_K_M

Run and chat with the model

lemonade run user.MixupModels-Q4_K_M

List all available models

lemonade list

laichaoyi commited on Jun 28

Commit

2f096b3

verified ·

1 Parent(s): 5dfb758

Upload models.json

Browse files

Files changed (1) hide show

models.json +2 -175

models.json CHANGED Viewed

@@ -396,180 +396,7 @@
     "type": "Others",
     "thumbnail": "https://i.ibb.co/msQPWSQ/sam3.jpg",
     "url": "https://huggingface.co/Andyhere/Z-images_models/resolve/main/SAM3.zip"
-  },
-  {
-    "model name": "Krea-2-Base-Q4_K_M.gguf",
-    "type": "base model",
-    "base": "krea2",
-    "thumbnail": "https://huggingface.co/krea/Krea-2-Raw/resolve/main/images/raw-header.jpg",
-    "url": "https://huggingface.co/realrebelai/KREA-2_GGUFs/resolve/main/BASE/Krea-2-Base-Q4_K_M.gguf",
-    "text_encoder": "Qwen3VL-4B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3VL-4B-Instruct-Q4_K_M.gguf",
-    "vae": "wan_2.1_vae.safetensors",
-    "vae_url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors"
-  },
-  {
-    "model name": "Krea-2-Turbo-Q4_K_M.gguf",
-    "type": "base model",
-    "base": "krea2",
-    "thumbnail": "https://huggingface.co/krea/Krea-2-Turbo/resolve/main/images/turbo-header.jpg",
-    "url": "https://huggingface.co/realrebelai/KREA-2_GGUFs/resolve/main/TURBO/Krea-2-Turbo-Q4_K_M.gguf",
-    "text_encoder": "Qwen3VL-4B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct-GGUF/resolve/main/Qwen3VL-4B-Instruct-Q4_K_M.gguf",
-    "vae": "wan_2.1_vae.safetensors",
-    "vae_url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors"
-  },
-  {
-    "model name": "boogu_image_base_bf16.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_base_bf16.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "runtime_status": "recommended_safe"
-  },
-  {
-    "model name": "boogu_image_edit_bf16.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_edit_bf16.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "llm_vision": "mmproj-F16.gguf",
-    "llm_vision_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/mmproj-F16.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "runtime_status": "recommended_safe"
-  },
-  {
-    "model name": "boogu_image_base_fp8_scaled.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_base_fp8_scaled.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "runtime_status": "experimental_blocked_by_default",
-    "runtime_note": "May load but can generate blank/invalid output on bundled sd-cli. Set boogu_allow_fp8_scaled=true to test."
-  },
-  {
-    "model name": "boogu_image_base_nvfp4.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_base_nvfp4.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors"
-  },
-  {
-    "model name": "boogu_image_edit_fp8_scaled.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_edit_fp8_scaled.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "llm_vision": "mmproj-F16.gguf",
-    "llm_vision_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/mmproj-F16.gguf",
-    "runtime_status": "experimental_blocked_by_default",
-    "runtime_note": "May load but can generate blank/invalid output on bundled sd-cli. Set boogu_allow_fp8_scaled=true to test."
-  },
-  {
-    "model name": "boogu_image_edit_nvfp4.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_edit_nvfp4.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "llm_vision": "mmproj-F16.gguf",
-    "llm_vision_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/mmproj-F16.gguf"
-  },
-  {
-    "model name": "boogu_image_edit_int8_convrot.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_edit_int8_convrot.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "llm_vision": "mmproj-F16.gguf",
-    "llm_vision_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/mmproj-F16.gguf",
-    "runtime_status": "blocked_by_safe_mode",
-    "runtime_note": "Bundled sd-cli does not support Boogu I8/int8_convrot tensors."
-  },
-  {
-    "model name": "boogu_image_turbo_fp8_scaled.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_turbo_fp8_scaled.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "runtime_status": "experimental_blocked_by_default",
-    "runtime_note": "May load but can generate blank/invalid output on bundled sd-cli. Set boogu_allow_fp8_scaled=true to test."
-  },
-  {
-    "model name": "boogu_image_turbo_nvfp4.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_turbo_nvfp4.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors"
-  },
-  {
-    "model name": "boogu_image_turbo_hotfix_bf16.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_turbo_hotfix_bf16.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "runtime_status": "recommended_safe"
-  },
-  {
-    "model name": "boogu_image_turbo_hotfix_int8_convrot.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_turbo_hotfix_int8_convrot.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors",
-    "runtime_status": "blocked_by_safe_mode",
-    "runtime_note": "Bundled sd-cli does not support Boogu I8/int8_convrot tensors."
-  },
-  {
-    "model name": "boogu_image_turbo_hotfix_nvfp4.safetensors",
-    "type": "base model",
-    "base": "boogu",
-    "thumbnail": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/images/boogu.jpg",
-    "url": "https://huggingface.co/Comfy-Org/Boogu-Image/resolve/main/diffusion_models/boogu_image_turbo_hotfix_nvfp4.safetensors",
-    "text_encoder": "Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "text_encoder_url": "https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF/resolve/main/Qwen3-VL-8B-Instruct-Q4_K_M.gguf",
-    "vae": "ae.safetensors",
-    "vae_url": "https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors"
   }
 ]

     "type": "Others",
     "thumbnail": "https://i.ibb.co/msQPWSQ/sam3.jpg",
     "url": "https://huggingface.co/Andyhere/Z-images_models/resolve/main/SAM3.zip"
   }
 ]