Instructions to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF 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 hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

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 hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

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 hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

Use Docker

docker model run hf.co/hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-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": "hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

Ollama
How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with Ollama:
```
ollama run hf.co/hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K
```

Unsloth Studio

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-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 hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-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 hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF to start chatting

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

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": "hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with Docker Model Runner:
```
docker model run hf.co/hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K
```

Lemonade

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-IK-K-GGUF-Q6_K

List all available models

lemonade list

Hermes Agent

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

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 hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K

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 "hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF:Q6_K" \
  --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"

Qwen3.6-35B-A3B — ik_llama IK_K quants (GGUF)

Self-quantized IK_K GGUFs of Qwen/Qwen3.6-35B-A3B — a 35B Mixture-of-Experts (~3B active), so it decodes at small-model speed. Quantized with an importance matrix (qwen35moe.imatrix, included) using ik_llama.cpp's IK_K quant types, which give noticeably better quality-per-bit than standard K-quants on this MoE.

⚠️ These require ik_llama.cpp. The IQ*_K types are an ik_llama extension and will NOT load in mainline llama.cpp, LM Studio, Ollama, or koboldcpp. If you need a portable quant, use a standard Q4_K_M/Q5_K_M GGUF instead.

Files

File	Quant	Size
`qwen35moe-IQ4_K.gguf`	IQ4_K	19.7 GB
`qwen35moe-IQ5_K.gguf`	IQ5_K	24.0 GB
`qwen35moe-IQ6_K.gguf`	IQ6_K	28.8 GB
`qwen35moe.imatrix`	imatrix used for quantization	0.11 GB

IQ4_K fits a single 24 GB GPU with room for context; IQ5_K / IQ6_K are for more VRAM or dual-GPU.

Usage (ik_llama.cpp)

Build ik_llama.cpp, then:

./build/bin/llama-server \
  -m qwen35moe-IQ4_K.gguf \
  -ngl 99 -fa 1 -c 32768 \
  -ctk q8_0 -ctv q8_0 \
  -fmoe -rtr \
  --jinja --host 127.0.0.1 --port 8080

Flag notes (ik_llama dialect differs from mainline):

-fa 1 — flash attention (not --flash-attn on).
-fmoe — ik_llama's fused-MoE kernel; meaningfully faster MoE decode. Recommended for this model.
-rtr — run-time tensor repack for your GPU; can speed up decode on some setups (optional).
Do NOT use -mtp — speculative decoding regresses on MoE (measured ~−28% on this model). These quants also ship no MTP head. Leave it off.
-ub 512 (default) is fastest here; -ub 2048 is ~8% slower on this MoE.

Single-stream decode is very fast for a 35B thanks to the ~3B active params — on the order of 175–200+ t/s at IQ4_K on a single modern 24 GB GPU.

Credits & license

Base model: Qwen/Qwen3.6-35B-A3B, Apache-2.0. Quantized locally with ik_llama.cpp + imatrix. Quant types courtesy of ik_llama.cpp.

Downloads last month: 120

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

6-bit

Model tree for hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(764)

this model