Instructions to use lqfdjbf32n/Qwen3-4B-Stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lqfdjbf32n/Qwen3-4B-Stage2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B")
model = PeftModel.from_pretrained(base_model, "lqfdjbf32n/Qwen3-4B-Stage2")

llama-cpp-python

How to use lqfdjbf32n/Qwen3-4B-Stage2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lqfdjbf32n/Qwen3-4B-Stage2",
	filename="qwen4b-s2-Q4_K_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 lqfdjbf32n/Qwen3-4B-Stage2 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 lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lqfdjbf32n/Qwen3-4B-Stage2: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 lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lqfdjbf32n/Qwen3-4B-Stage2: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 lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

Use Docker

docker model run hf.co/lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

LM Studio
Jan

vLLM

How to use lqfdjbf32n/Qwen3-4B-Stage2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lqfdjbf32n/Qwen3-4B-Stage2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lqfdjbf32n/Qwen3-4B-Stage2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

Ollama
How to use lqfdjbf32n/Qwen3-4B-Stage2 with Ollama:
```
ollama run hf.co/lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M
```

Unsloth Studio

How to use lqfdjbf32n/Qwen3-4B-Stage2 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 lqfdjbf32n/Qwen3-4B-Stage2 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 lqfdjbf32n/Qwen3-4B-Stage2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lqfdjbf32n/Qwen3-4B-Stage2 to start chatting

How to use lqfdjbf32n/Qwen3-4B-Stage2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_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": "lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lqfdjbf32n/Qwen3-4B-Stage2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lqfdjbf32n/Qwen3-4B-Stage2: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 lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use lqfdjbf32n/Qwen3-4B-Stage2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lqfdjbf32n/Qwen3-4B-Stage2: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 "lqfdjbf32n/Qwen3-4B-Stage2: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"

Docker Model Runner
How to use lqfdjbf32n/Qwen3-4B-Stage2 with Docker Model Runner:
```
docker model run hf.co/lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M
```

Lemonade

How to use lqfdjbf32n/Qwen3-4B-Stage2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-Stage2-Q4_K_M

List all available models

lemonade list

Qwen3-4B — Stage 2 (Reasoning Injection)

A 4B parameter model built on top of Stage 1, injected with high-quality Claude Opus reasoning traces and curated chain-of-thought data. This is Stage 2 of a multi-stage training pipeline — focused on deep reasoning, structured thinking, and multi-step problem solving.

Model Details

Base Model: unsloth/Qwen3-4B
Parameters: 4B
Architecture: Qwen3 (dense, pure text)
Training: Stage 1 LoRA → merge → Stage 2 LoRA → merge
License: Apache 2.0
Language: English (multilingual via base model)

Files

File	Description
`adapter_model.safetensors`	Stage 2 LoRA adapter weights (unmerged, applied on top of S1)
`adapter_config.json`	LoRA configuration
`qwen4b-s2-Q4_K_M.gguf`	Quantized GGUF (Q4_K_M, ~2.4GB)
`tokenizer.json`	Tokenizer

Training Details

Stage 1 → Stage 2 Pipeline

This model is trained in two sequential stages:

Stage 1 — General Foundation (~308k samples, 2 epochs) General chat, instruction following, math, coding, factual QA. See Qwen3-4B-Stage1 for details.

Stage 2 — Reasoning Injection (~5,576 samples, 2 epochs) High-quality Claude Opus reasoning traces and curated chain-of-thought data injected on top of Stage 1.

Stage 2 Dataset Mix

Dataset	Samples	Purpose
TeichAI/claude-4.5-opus-high-reasoning-250x	250	Claude Opus 4.5 high reasoning traces
nohurry/Opus-4.6-Reasoning-3000x-filtered	2,326	Claude 4.6 Opus reasoning traces
bespokelabs/Bespoke-Stratos-17k	3,000	Curated chain-of-thought

Total Stage 2: ~5,576 samples, 2 epochs

Stage 2 Hyperparameters

Parameter	Value
LoRA rank	32
LoRA alpha	32
Learning rate	5e-5 cosine
Epochs	2
Sequence length	4096
Batch size	2 (effective 32)
Optimizer	adamw
Final loss	0.5117

Hardware

Trained on AMD Instinct MI300X (192GB VRAM), ROCm 6.2.4, Unsloth 2026.3.3, PyTorch 2.7.1+rocm6.2.4. Stage 2 runtime: ~4.4 hours.

Usage

Ollama (GGUF)

ollama run hf.co/lqfdjbf32n/Qwen3-4B-Stage2:Q4_K_M

llama.cpp

llama-cli -m qwen4b-s2-Q4_K_M.gguf \
    -p "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nYour question here<|im_end|>\n<|im_start|>assistant\n" \
    -n 512

Python (LoRA adapter — requires Stage 1 first)

from unsloth import FastLanguageModel
from peft import PeftModel
import torch

# Load base
model, tokenizer = FastLanguageModel.from_pretrained(
    "unsloth/Qwen3-4B",
    max_seq_length=4096,
    dtype=torch.bfloat16,
    load_in_4bit=False,
)

# Apply Stage 1
model = PeftModel.from_pretrained(model, "lqfdjbf32n/Qwen3-4B-Stage1")
model = model.merge_and_unload()

# Apply Stage 2
model = PeftModel.from_pretrained(model, "lqfdjbf32n/Qwen3-4B-Stage2")
model = model.merge_and_unload()

Strengths

Structured <think>...</think> reasoning blocks for complex problems
Multi-step math and science problem solving
Claude Opus reasoning style distilled into 4B parameters
Natural casual conversation (inherited from Stage 1)
Auto language detection (English/Indonesian)

Limitations

Stage 2 only — requires Stage 1 as foundation
English primary (multilingual via base model)
Not suitable for production without validation
Complex reasoning may still fail on hardest problems

Part of a Series

Model	Description
Qwen2.5-0.5B-ReasonChat	0.5B edge model, reasoning + chat merged
Qwen3-4B-Stage1	4B general foundation
Qwen3-4B-Stage2	4B + Claude reasoning injection (this model)
Qwen3-4B-Stage3	4B + alignment (coming soon)

Downloads last month: 8

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for lqfdjbf32n/Qwen3-4B-Stage2

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

unsloth/Qwen3-4B

Adapter

(31)

this model