Instructions to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 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 VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1: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 VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1: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 VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS

Use Docker

docker model run hf.co/VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS

LM Studio
Jan
Ollama
How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with Ollama:
```
ollama run hf.co/VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS
```

Unsloth Studio

How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 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 VladHong/Qwen3-4B-Instruct-NoThink-V2.1 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 VladHong/Qwen3-4B-Instruct-NoThink-V2.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VladHong/Qwen3-4B-Instruct-NoThink-V2.1 to start chatting

How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1: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": "VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with Docker Model Runner:
```
docker model run hf.co/VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS
```

Lemonade

How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3-4B-Instruct-NoThink-V2.1-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1: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 VladHong/Qwen3-4B-Instruct-NoThink-V2.1:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VladHong/Qwen3-4B-Instruct-NoThink-V2.1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VladHong/Qwen3-4B-Instruct-NoThink-V2.1: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 "VladHong/Qwen3-4B-Instruct-NoThink-V2.1: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"

Qwen3-4B Instruct No-Think V2.1

Finetuned from Unsloth/Qwen3-4B-Instruct-2507 using QLoRA + Unsloth. Trained to respond directly without chain-of-thought (<think> blocks stripped from all training data).

What's New in V2.1: The best I can afford on free Kaggle GPU

V2.1 further expands the training data to 7 datasets covering Gemini, Claude, and GPT-sourced reasoning traces, and was trained on Kaggle's dual T4 GPU environment (though only one GPU was used for training). Dataset size after deduplication contains ~4,752 examples with MinHash-based similarity filtering at 0.4 Jaccard threshold.

Training Data

Dataset	Source Model
TeichAI/gemini-3-pro-preview-high-reasoning-250x	Gemini
TeichAI/gemini-3-pro-preview-high-reasoning-1000x	Gemini
Roman1111111/gemini-3.1-pro-hard-high-reasoning	Gemini
crownelius/Opus-4.6-Reasoning-3300x	Claude
TeichAI/claude-4.5-opus-high-reasoning-250x	Claude
TeichAI/claude-sonnet-4.5-high-reasoning-250x	Claude
TeichAI/gpt-5.2-high-reasoning-250x	GPT

~7,322 rows loaded, ~4,752 after MinHash deduplication (threshold 0.4). <think> blocks stripped from all assistant turns before training.

Training Details

Parameter	Value
Method	QLoRA (4-bit NF4) + Unsloth
LoRA rank	16
LoRA alpha	16
Epochs	1
Steps	594
Batch size	2 per device × 4 gradient accumulation = 8 effective
Learning rate	1e-4 (cosine schedule)
Max seq length	2048
Optimizer	AdamW 8-bit
Hardware	Kaggle Tesla T4 (14.56 GB VRAM)
Training time	~7h 23min
Trainable params	33M / 4.05B (0.81%)
Peak VRAM	~10.2 GB

Training used train_on_responses_only — loss computed on assistant completions only.

Files

*.gguf — IQ4_XS quantized, ready for LM Studio / Ollama / llama.cpp
lora-adapter/ — Raw LoRA weights for merging with the base model

Usage (Ollama)

ollama run VladHong/Qwen3-4B-Instruct-NoThink-V2.1

License Note

Base model is Apache 2.0. Training data includes AI-generated content — review upstream dataset terms before commercial use.

Downloads last month: 16

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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

VladHong
/

Qwen3-4B-Instruct-NoThink-V2.1

Qwen3-4B Instruct No-Think V2.1

What's New in V2.1: The best I can afford on free Kaggle GPU

Training Data

Training Details

Files

Usage (Ollama)

License Note

Datasets used to train VladHong/Qwen3-4B-Instruct-NoThink-V2.1