Instructions to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF",
	filename="qwen36-35b-a3b-IQ2_M.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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

Use Docker

docker model run hf.co/KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

LM Studio
Jan

vLLM

How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KikoCis/Qwen3.6-35B-A3B-IQ2_M-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": "KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

Ollama
How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with Ollama:
```
ollama run hf.co/KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M
```

Unsloth Studio

How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF to start chatting

How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

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": "KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

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 KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with Docker Model Runner:
```
docker model run hf.co/KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M
```

Lemonade

How to use KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF:IQ2_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-IQ2_M-GGUF-IQ2_M

List all available models

lemonade list

Qwen3.6-35B-A3B — IQ2_M (domain imatrix)

Custom IQ2_M quantization of Qwen/Qwen3.6-35B-A3B with a domain-mixed importance matrix calibrated on code + agentic + CLI traces.

Size: 11.1 GB
BPW: 2.69
Architecture: Hybrid GatedDeltaNet + MoE (256 experts, 8+1 active per token, 35B total / 3B active)
Calibration: domain-mixed imatrix (45% code, 45% agentic/tool-use, 10% general)

Benchmark comparison — Cross-model, cross-architecture

First public HumanEval+/MBPP+/BFCL evaluation of Qwen3.6-35B-A3B quantizations.

Note on BFCL scores: All BFCL scores reported here use our internal simplified evaluation (single-function-call subset with custom prompt/scoring), NOT the official Berkeley Function Calling Leaderboard methodology. Our scores are not directly comparable to the official leaderboard. We are working on running the official BFCL evaluation for comparable numbers.

Model	Size	Active	HumanEval+	MBPP+	BFCL v3	NL2Bash F1
Gemma 4 31B IQ2_M (sibling)	10.4 GB	31B	88.41%	82.01%	92.25%	84.71%
Qwen3.6 Q8_0 (≈f16 baseline)	35.2 GB	3B	81.10%	82.80%	95.25%	—
Qwen3.6 Unsloth UD-IQ2_M	11.0 GB	3B	82.32%	79.37%	94.25%	—
Qwen3.6 IQ2_M (this repo)	11.1 GB	3B	80.49%	78.31%	94.75%	81.63%
Gemma 4 E4B Q8_0	7.8 GB	4.5B	73.78%	73.28%	93.75%	79.75%
Gemma 4 31B IQ1_M	7.4 GB	31B	21.34%	40.50%	86.75%	53.89%

Key findings

This repo beats Unsloth UD-IQ2_M on BFCL (+0.5pt, 94.75 vs 94.25) — domain-mixed imatrix calibration with 45% agentic traces pays off for tool-calling
Gemma 4 31B IQ2_M remains king for pure code at 10 GB — HumanEval+ 88.41% is unmatched
Qwen3.6 MoE efficiency is remarkable: 3B active params at 11 GB scores 94.75% BFCL, competing with 31B dense models
Sub-8 GB tier: Gemma 4 E4B Q8_0 (7.8 GB) dominates over the 31B IQ1_M (7.4 GB) on every metric — ultra-aggressive quantization of large models loses to small models at full precision

Recommendation by use case

Best for code (any size): Gemma 4 31B IQ2_M (10.4 GB)
Best for agentic/tool-calling: This repo — Qwen3.6 IQ2_M (11.1 GB)
Best sub-8 GB all-rounder: Gemma 4 E4B Q8_0 (7.8 GB)

Quickstart

huggingface-cli download KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF qwen36-35b-a3b-IQ2_M.gguf --local-dir .

llama-cli -m qwen36-35b-a3b-IQ2_M.gguf -ngl 99 --ctx-size 8192 --temp 0.1 \
  -p "Write a Python function to find the longest palindromic substring"

Files

qwen36-35b-a3b-IQ2_M.gguf — quantized weights (11.1 GB)
qwen36-35b-a3b-domain.imatrix — importance matrix used for calibration

License

Apache 2.0.

Real-World Agent Test Warning (April 2026)

Benchmark scores do not predict agent capability. In Docker-based autonomous testing, fine-tuned E4B models (95% BFCL) scored 0/10 while the unfine-tuned base scored 6/10. Fine-tuning for BFCL destroyed general reasoning (error recovery, strategy adaptation, anti-repetition). Fine-tuned E4B models have been withdrawn.

For autonomous agent tasks, use the base Gemma 4 model or a larger model at higher BPW. See: The Benchmark Trap — Full Study

Downloads last month: 550

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

2-bit

Model tree for KikoCis/Qwen3.6-35B-A3B-IQ2_M-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(510)

this model

KikoCis
/

Qwen3.6-35B-A3B-IQ2_M-GGUF