Instructions to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF",
	filename="InstinctRazor-Qwen3.5-122B-A10B-IQ3_XXS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama-cli -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama-cli -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

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 General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./llama-cli -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

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 General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

Use Docker

docker model run hf.co/General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

LM Studio
Jan

vLLM

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-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": "General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

Ollama
How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with Ollama:
```
ollama run hf.co/General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS
```

Unsloth Studio

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-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 General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-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 General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF to start chatting

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

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": "General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

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 General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with Docker Model Runner:
```
docker model run hf.co/General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS
```

Lemonade

How to use General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF:IQ3_XXS

Run and chat with the model

lemonade run user.InstinctRazor-Qwen3.5-122B-A10B-GGUF-IQ3_XXS

List all available models

lemonade list

MTP layer

by engrtipusultan - opened 10 days ago

Discussion

engrtipusultan

10 days ago

It does not have mtp layer can you upload without MTP stripped?

Also when you plan to upload coding optimized version?

GM717

General-Instinct org 10 days ago

I tried compiling it with MTP and DFlash, but it hurt the output quality quite a bit, so I decided not to release it with the MTP layer.

We're still working on decode speed optimization. Hopefully, we'll have another version focused on faster decoding performance available soon.

engrtipusultan

10 days ago

•

edited 10 days ago

I did not quite get that. Keeping the MTP layer does not mean it is enabled and Dflash is not supported in mailline llama.cpp hence in lmstudio etc.

engrtipusultan

10 days ago

Hopefully you can add some benchmarks when you upload final version against the original model for accuracy and speed.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment