Instructions to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS 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 majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

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 majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

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 majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Use Docker

docker model run hf.co/majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

LM Studio
Jan

vLLM

How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Ollama
How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with Ollama:
```
ollama run hf.co/majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
```
Unsloth Desktop

How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with Docker Model Runner:
```
docker model run hf.co/majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
```

Lemonade

How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

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 majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

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 "majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS:IQ4_XS" \
  --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"

majentik commited on Apr 13

Commit

13cabc6

verified ·

1 Parent(s): d74472f

Add model card

Browse files

Files changed (1) hide show

README.md +70 -0

README.md ADDED Viewed

	@@ -0,0 +1,70 @@

+---
+library_name: gguf
+base_model: Qwen/Qwen3.5-27B
+tags:
+  - gguf
+  - rotorquant
+  - kv-cache-quantization
+  - qwen
+  - qwen3
+  - moe
+  - thinking
+  - llama-cpp
+  - quantized
+license: apache-2.0
+---
+# Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS
+GGUF IQ4_XS weight-quantized variant of [Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B) with **RotorQuant** KV cache compression for efficient inference with llama.cpp, Ollama, and LM Studio.
+## Overview
+This model combines two compression techniques:
+- **GGUF IQ4_XS weight quantization** — reduces model size from ~54GB to ~14 GB
+- **RotorQuant KV cache compression** — block-diagonal rotations (Clifford algebra) for 3-bit KV cache, 5.3x faster prefill
+## Quickstart
+### llama.cpp
+```bash
+llama-cli -m Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS.gguf \
+  --cache-type-k planar3 --cache-type-v iso3 \
+  -p "Explain quantum computing"
+```
+### Ollama
+```bash
+ollama run majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS
+```
+### LM Studio
+Download the GGUF file and load in LM Studio. Enable RotorQuant KV cache in advanced settings.
+## Specifications
+| Property | Value |
+|----------|-------|
+| Base Model | Qwen/Qwen3.5-27B |
+| Parameters | 27B hybrid MoE |
+| Weight Quantization | GGUF IQ4_XS |
+| KV Cache | RotorQuant 3-bit (planar/iso) |
+| File Size | ~14 GB |
+| License | Apache 2.0 |
+| Compatible | llama.cpp, Ollama, LM Studio, koboldcpp |
+## What is RotorQuant?
+RotorQuant applies block-diagonal rotations (Clifford algebra) for KV cache compression. When used with llama.cpp's `--cache-type-k planar3 --cache-type-v iso3` flags:
+| Metric | RotorQuant | TurboQuant |
+|--------|-----------|-----------|
+| Prefill Speed | 3,822 tok/s | 722 tok/s |
+| Decode Speed | 119 tok/s | 93 tok/s |
+| Perplexity | 6.91 | 7.07 |
+## See Also
+- [RotorQuant GitHub](https://github.com/scrya-com/rotorquant)
+- [Base model](https://huggingface.co/Qwen/Qwen3.5-27B)
+- [MLX variants](https://huggingface.co/majentik/Qwen3.5-27B-RotorQuant-MLX-4bit)