Instructions to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-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 Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-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 Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_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 Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_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 Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF with Ollama:
```
ollama run hf.co/Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

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": "Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M
```

Lemonade

How to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-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 Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_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 Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M

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 "Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF:Q4_K_M" \
  --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"

Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1

First attempt at improving reasoning abilities for Qwen3.5 4b model based on the open crownelius/Opus-4.6-Reasoning-3300x dataset.

Evals

I didn't have the patience to run too many evals, but I definitely noticed vibes wise it was a lot more "opus"-like (in a good way) in it's reasoning and responses, base Qwen3.5 4b kinda rambles on. Seemed smarter... The one eval I did was was the latest LiveBench Reasoning benchmarks, and here are the results:

Model	Spatial	Zebra Puzzle	Reasoning Avg
qwen3.5-4b (Base)	4.0	18.75	11.4
Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1	24.0	19.0	21.5
Δ Improvement	+20.0	+0.25	+10.1
% Improvement	+500%	+1.3%	+88.6%

Notes

For v2 of this model, I need to fix the thinking template. It seems like the model ALWAYS does reasoning due to the way I templated the dataset, so I'm doing another training run with explicit think or no think rows. (hopefully that works?).

Also, I don't know much about training models or ML, I'm a Software Engineer who uses a lot of AI. I just started, and this was pretty much the first real model I've ever trained, so please be nice!

Training

I trained this on a single RTX 4060ti with 16GB VRAM, took around 2 or 3 hours.

Acknowledgements

crownelius for the cleaned dataset
unsloth for the training arch
pewdiepie for inspiring me to try training models (seriously, lol)

Downloads last month: 20

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(401)

this model

Aisho67
/

Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF

Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1

Evals

Notes

Training

Acknowledgements

Model tree for Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF

Dataset used to train Aisho67/Qwen3.5-4b-Opus-4.6-Reasoning-Distilled-v1-GGUF