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

InstinctRazor — Qwen3.5-122B-A10B · IQ3_XXS GGUF

A 122B hybrid Gated-DeltaNet MoE (256 experts, 8 active) — packed to 48 GiB so it runs on one 80 GB GPU (or a small card + CPU offload). Quantized from the original BF16 with an importance matrix (math + code + general calibration), via llama.cpp.

Framework, recipe, and full reproduction: https://github.com/General-Instinct/InstinctRazor

Speed (llama.cpp, this artifact)

1× H100-80GB, all layers on GPU: 115.9 tok/s decode (prefill ≈2541 tok/s).
Small card + CPU expert-offload (--n-cpu-moe 48, peak ≈7.6 GiB VRAM): 45.7 tok/s decode — runs on an 8 GB GPU + ≈48 GiB system RAM.

Run

# full GPU
llama-cli -m InstinctRazor-Qwen3.5-122B-A10B-IQ3_XXS.gguf -ngl 999 -fa on -p "Your prompt"
# small card + CPU offload (routed experts on CPU)
llama-cli -m InstinctRazor-Qwen3.5-122B-A10B-IQ3_XXS.gguf -ngl 999 --n-cpu-moe 48 -t 52 -p "Your prompt"
# multimodal (image input)
llama-cli -m InstinctRazor-Qwen3.5-122B-A10B-IQ3_XXS.gguf --mmproj InstinctRazor-Qwen3.5-122B-A10B-mmproj-f16.gguf --image pic.png -p "Describe the image"

Requires a llama.cpp build with qwen3_5_moe support (upstream, 2026-02+).

Scope & roadmap

This GGUF matches or beats the footprint-matched A4B on knowledge, reasoning, and multimodal-MMMU. Where it still trails — code (LiveCodeBench v6) and math / multimodal-math — the loss is largely token-inefficiency introduced by quantization, and is the target of OPD (on-policy distillation), a separate framework we'll open-source later. Eval absolutes are subject to a same-harness validation gate; see the GitHub results/RESULTS.md for full per-number provenance.

Attribution

Quantization recipe + framework: General Instinct, released under Apache-2.0.

Downloads last month: 4,364

GGUF

Model size

122B params

Architecture

qwen35moe

Hardware compatibility

3-bit

Model tree for General-Instinct/InstinctRazor-Qwen3.5-122B-A10B-GGUF

Base model

Qwen/Qwen3.5-122B-A10B

Quantized

(121)

this model