Instructions to use RexTRO111/Qwen3-4B-MegaR3ASONER-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RexTRO111/Qwen3-4B-MegaR3ASONER-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RexTRO111/Qwen3-4B-MegaR3ASONER-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RexTRO111/Qwen3-4B-MegaR3ASONER-v1")
model = AutoModelForCausalLM.from_pretrained("RexTRO111/Qwen3-4B-MegaR3ASONER-v1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RexTRO111/Qwen3-4B-MegaR3ASONER-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RexTRO111/Qwen3-4B-MegaR3ASONER-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RexTRO111/Qwen3-4B-MegaR3ASONER-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RexTRO111/Qwen3-4B-MegaR3ASONER-v1

SGLang

How to use RexTRO111/Qwen3-4B-MegaR3ASONER-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RexTRO111/Qwen3-4B-MegaR3ASONER-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RexTRO111/Qwen3-4B-MegaR3ASONER-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RexTRO111/Qwen3-4B-MegaR3ASONER-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RexTRO111/Qwen3-4B-MegaR3ASONER-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RexTRO111/Qwen3-4B-MegaR3ASONER-v1 with Docker Model Runner:
```
docker model run hf.co/RexTRO111/Qwen3-4B-MegaR3ASONER-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-4B-MegaR3ASONER-v1

A full merged reasoning model created by merging the MegaR3ASONER LoRA into Qwen/Qwen3-4B-Thinking-2507.

Model type

This repository contains the complete merged Transformers model, not only the PEFT adapter. It can be loaded directly without PeftModel.

Base model: Qwen/Qwen3-4B-Thinking-2507
Merge dtype: BF16
Adapter source: RexTRO111/Qwen3-4B-MegaR3ASONER-LoRA-v1
Training hardware: NVIDIA A10G on Modal
Merge hardware: NVIDIA A10G on Modal

Preliminary evaluation

On the first 100 examples selected by EleutherAI's gsm8k_cot task:

Flexible extraction exact match: 88%
Strict match: 83%

This was a limited 100-question run, not a full GSM8K score and not a controlled base-versus-fine-tune comparison.

Loading

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "RexTRO111/Qwen3-4B-MegaR3ASONER-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

Limitations

It may produce an incorrect intermediate thought before correcting itself.
It can overthink simple prompts.
Long reasoning traces increase latency and cost.
Benchmark contamination has not been exhaustively ruled out.
Verify answers before high-stakes use.

Licensing note

The Qwen base model and every training dataset retain their own licenses and upstream terms. Review all applicable terms before redistribution or commercial use.

Downloads last month: 206

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for RexTRO111/Qwen3-4B-MegaR3ASONER-v1

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

(262)

this model

Quantizations

2 models

RexTRO111
/

Qwen3-4B-MegaR3ASONER-v1