Instructions to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx with Transformers:

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

pipe = pipeline("text-generation", model="parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx")
model = AutoModelForCausalLM.from_pretrained("parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx", 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]:]))

MLX

How to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx

SGLang

How to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx 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 "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx" \
    --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": "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx",
		"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 "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx" \
        --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": "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx with Docker Model Runner:
```
docker model run hf.co/parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx
```
Atomic Chat

parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx

The Model parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx was converted to MLX format from agentica-org/DeepScaleR-1.5B-Preview using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Citation

@misc{deepscaler2025,
  title={DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL},
  author={Michael Luo and Sijun Tan and Justin Wong and Xiaoxiang Shi and William Tang and Manan Roongta and Colin Cai and Jeffrey Luo and Tianjun Zhang and Erran Li and Raluca Ada Popa and Ion Stoica},
  year={2025},
  howpublished={\url{https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2}},
  note={Notion Blog}
  year={2025}
}

Downloads last month: 16

Safetensors

Model size

2B params

Tensor type

U32

F16

MLX

Hardware compatibility

8-bit

Model tree for parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Finetuned

agentica-org/DeepScaleR-1.5B-Preview

Quantized

(38)

this model

parole-study-viper
/

DeepScaleR-1.5B-Preview-Q8-mlx

parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx

Use with mlx

Citation

Model tree for parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx

Datasets used to train parole-study-viper/DeepScaleR-1.5B-Preview-Q8-mlx