Instructions to use majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Use Docker

docker model run hf.co/majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

LM Studio
Jan

vLLM

How to use majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS",
		"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/majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Ollama
How to use majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS with Ollama:
```
ollama run hf.co/majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
```
Unsloth Desktop

How to use majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS with Docker Model Runner:
```
docker model run hf.co/majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS
```

Lemonade

How to use majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-RotorQuant-GGUF-IQ4_XS:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B-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 Jul 20

Commit

ccd31ec

verified ·

1 Parent(s): c993ccd

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip

Browse files

Files changed (1) hide show

README.md +8 -19

README.md CHANGED Viewed

@@ -131,23 +131,14 @@ OLLAMA_KV_CACHE_TYPE=q8_0 OLLAMA_FLASH_ATTENTION=1 ollama run majentik/Qwen3.6-3
 | Modalities | Text + Image + Video (multimodal) |
 | Compatible Runtimes | llama.cpp, LM Studio, Ollama, koboldcpp |
-## What is RotorQuant?
-[RotorQuant](https://github.com/scrya-com/rotorquant) is a KV cache compression method based on Clifford algebra (Cl(3,0)) rotors. It was developed as a faster, more parameter-efficient alternative to Google's [TurboQuant](https://arxiv.org/abs/2504.19874) (ICLR 2026).
-Instead of applying a dense d×d random orthogonal rotation matrix (as TurboQuant does), RotorQuant uses lightweight block-diagonal rotations — independent 2D/4D rotations per pair/quartet — achieving O(d) complexity instead of O(d log d), fully parallelisable with no inter-element dependencies.
-**Benchmarks from the RotorQuant repository** (Llama 3.1 8B, RTX 5090 — results will vary by model and hardware):
-| Metric | RotorQuant (iso3) | TurboQuant | Standard q4_0 |
-|--------|-------------------|------------|---------------|
-| Prefill Speed | 3,822 tok/s | 722 tok/s | — |
-| Decode Speed | 119 tok/s | 93 tok/s | — |
-| Perplexity (PPL) | 6.91 | 7.07 | — |
-| KV Compression | ~5× vs FP16 | ~5× vs FP16 | ~4× vs FP16 |
-| Rotation Parameters | 4 per rotor | 16,384 per matrix | N/A |
-> **Note:** These benchmarks are from the RotorQuant repository using Llama 3.1 8B on an RTX 5090. Performance on Qwen3.6-35B-A3B will differ. Independent benchmarks for this specific model are welcome — please open a discussion if you have results to share.
 ## Current Status of RotorQuant in the Ecosystem
@@ -199,7 +190,6 @@ For VRAM-constrained setups, standard q8_0 KV cache quantization already halves
 | Variant | Runtime | Approx size | Use case |
 |---|---|---|---|
-| [RotorQuant](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
 | **RotorQuant-GGUF-IQ4_XS** | llama.cpp | ~30 GB | Lossy 4-bit, low-RAM CPU/edge |
 | [RotorQuant-GGUF-Q2_K](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-gguf-Q2_K) | llama.cpp | ~21 GB | Lossy, low-RAM CPU/edge |
 | [RotorQuant-GGUF-Q3_K_M](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-gguf-Q3_K_M) | llama.cpp | ~27 GB | Smaller 3-bit, CPU-friendly |
@@ -212,10 +202,9 @@ For VRAM-constrained setups, standard q8_0 KV cache quantization already halves
 | [RotorQuant-MLX-5bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-mlx-5bit) | mlx-lm | ~27 GB | Apple Silicon, higher fidelity |
 | [RotorQuant-MLX-6bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-mlx-6bit) | mlx-lm | ~32 GB | Apple Silicon, near-lossless |
 | [RotorQuant-MLX-8bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-mlx-8bit) | mlx-lm | ~41 GB | Apple Silicon reference |
-| [TurboQuant](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
 | [TurboQuant-MLX-2bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-2bit) | mlx-lm | ~11 GB | Apple Silicon, smallest |
 | [TurboQuant-MLX-3bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-3bit) | mlx-lm | ~16 GB | Apple Silicon, small |
 | [TurboQuant-MLX-4bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-4bit) | mlx-lm | ~22 GB | Apple Silicon balanced |
 | [TurboQuant-MLX-5bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-5bit) | mlx-lm | ~27 GB | Apple Silicon, higher fidelity |
 | [TurboQuant-MLX-6bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-6bit) | mlx-lm | ~32 GB | Apple Silicon, near-lossless |
-| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-8bit) | mlx-lm | ~41 GB | Apple Silicon reference |

 | Modalities | Text + Image + Video (multimodal) |
 | Compatible Runtimes | llama.cpp, LM Studio, Ollama, koboldcpp |
+## About the RotorQuant / TurboQuant labels
+RotorQuant and TurboQuant are this project's **release labels**, not distinct
+quantization algorithms — for any given tier, both brand repos carry
+byte-identical weights produced with the standard MLX / llama.cpp quantizers.
+No brand-specific speedup is claimed or measured. The KV-cache fork these
+labels originally referred to is legacy; for KV-cache memory savings use the
+upstream options described above (`-ctk/-ctv q8_0`, `OLLAMA_KV_CACHE_TYPE`).
 ## Current Status of RotorQuant in the Ecosystem
 | Variant | Runtime | Approx size | Use case |
 |---|---|---|---|
 | **RotorQuant-GGUF-IQ4_XS** | llama.cpp | ~30 GB | Lossy 4-bit, low-RAM CPU/edge |
 | [RotorQuant-GGUF-Q2_K](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-gguf-Q2_K) | llama.cpp | ~21 GB | Lossy, low-RAM CPU/edge |
 | [RotorQuant-GGUF-Q3_K_M](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-gguf-Q3_K_M) | llama.cpp | ~27 GB | Smaller 3-bit, CPU-friendly |
 | [RotorQuant-MLX-5bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-mlx-5bit) | mlx-lm | ~27 GB | Apple Silicon, higher fidelity |
 | [RotorQuant-MLX-6bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-mlx-6bit) | mlx-lm | ~32 GB | Apple Silicon, near-lossless |
 | [RotorQuant-MLX-8bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-rotorquant-mlx-8bit) | mlx-lm | ~41 GB | Apple Silicon reference |
 | [TurboQuant-MLX-2bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-2bit) | mlx-lm | ~11 GB | Apple Silicon, smallest |
 | [TurboQuant-MLX-3bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-3bit) | mlx-lm | ~16 GB | Apple Silicon, small |
 | [TurboQuant-MLX-4bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-4bit) | mlx-lm | ~22 GB | Apple Silicon balanced |
 | [TurboQuant-MLX-5bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-5bit) | mlx-lm | ~27 GB | Apple Silicon, higher fidelity |
 | [TurboQuant-MLX-6bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-6bit) | mlx-lm | ~32 GB | Apple Silicon, near-lossless |
+| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/qwen3.6-35b-a3b-turboquant-mlx-8bit) | mlx-lm | ~41 GB | Apple Silicon reference |