Instructions to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix",
	filename="qwen3.6-35B-A3B-IQ4_XS.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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix 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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix: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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix: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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

Use Docker

docker model run hf.co/Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

LM Studio
Jan

vLLM

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

Ollama
How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with Ollama:
```
ollama run hf.co/Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS
```

Unsloth Studio

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix 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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix 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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix to start chatting

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

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": "Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix: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 Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix: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 "Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix: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"

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

Lemonade

How to use Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Krasnopjorovs/Qwen3.6-35B-A3B-IQ4_XS-Imatrix:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-IQ4_XS-Imatrix-IQ4_XS

List all available models

lemonade list

Qwen3.6-35B-A3B-IQ4_XS-Imatrix / README.md

Krasnopjorovs

Update README.md

b24a11d verified 3 months ago

preview code

Raw

History Blame Contribute Delete

2.3 kB

	---
	base_model:
	- Qwen/Qwen3.6-35B-A3B
	library_name: gguf
	license: apache-2.0
	tags:
	- qwen
	- qwen3.6
	- moe
	- gguf
	- iq4_xs
	- imatrix
	- text-generation
	pipeline_tag: text-generation
	---

	# Qwen 3.6 35B A3B - GGUF (IQ4_XS) with Custom Imatrix

	## 🚀 Model Overview
	This repository contains a highly optimized, custom-quantized GGUF version of Qwen 3.6 35B A3B.
	It leverages the Mixture-of-Experts (MoE) architecture, possessing 35 Billion total parameters but activating only ~3 Billion parameters per token during inference. This provides flagship-level intelligence (advanced logic, coding, multilingual RAG) at unprecedented speeds.

	## 🧠 Custom Quantization (The "Reapmix" Imatrix)
	Unlike standard uniform quantizations that often degrade a model's reasoning capabilities, this specific build was compressed using a Custom Importance Matrix (`.imatrix`).
	- Calibration Dataset: Computed over 1.1 million strictly selected tokens (`reapmix_imatrix.txt`).
	- Format: `IQ4_XS` (i-quants, Extra Small).
	- Bit-per-weight (BPW): ~4.32.
	- Result: The model size was dramatically reduced from ~66.1 GB to just 17.8 GB, preserving near 100% of its deductive reasoning, JSON-formatting discipline, and constraint satisfaction abilities.

	## 💻 Hardware Requirements
	This build is designed to maximize VRAM efficiency, allowing a 35B model to fit comfortably on consumer and workstation GPUs while leaving massive headroom for the context window.
	- File Size: ~17.8 GB.
	- Minimum VRAM: 24 GB (e.g., RTX 3090, 4090, A5000, RTX 5000) for full GPU offload with 8k-16k context.

	## 🛠️ How to Run

	### 1. Using `llama.cpp` (Web Server Mode)
	The most efficient way to run this model is via the `llama-server` binary with maximum GPU offload.

	```bash
	./llama-server -m qwen3.6-35B-A3B-IQ4_XS.gguf -c 32768 -ngl 99 --host 0.0.0.0 --port 8080

	🎯 Use Cases Tested
	- This specific quantization has been heavily verified against:
	- Cross-Language RAG: Seamlessly bridging English data-center infrastructure rules with Russian situational queries.
	- Algorithmic Coding: Generating O(N) complexity Python scripts without regex, strictly following constraint rules.
	- Strict Formatting: Outputting pure, valid JSON objects without markdown wrappers or conversational filler.