Instructions to use YifeiZuo/Parallax-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YifeiZuo/Parallax-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="YifeiZuo/Parallax-0.6B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("YifeiZuo/Parallax-0.6B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YifeiZuo/Parallax-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YifeiZuo/Parallax-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YifeiZuo/Parallax-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YifeiZuo/Parallax-0.6B

SGLang

How to use YifeiZuo/Parallax-0.6B 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 "YifeiZuo/Parallax-0.6B" \
    --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": "YifeiZuo/Parallax-0.6B",
		"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 "YifeiZuo/Parallax-0.6B" \
        --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": "YifeiZuo/Parallax-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YifeiZuo/Parallax-0.6B with Docker Model Runner:
```
docker model run hf.co/YifeiZuo/Parallax-0.6B
```

Parallax-0.6B

Parallax (Parameterized Local Linear Attention) is an experimental language model that reuses the Qwen3 architecture but replaces softmax self-attention with the parallax op (attn_type="parallax"). This is the 0.6B-parameter model.

Reference: https://arxiv.org/abs/2605.29157

Model details


Parameters	~0.6B
Layers	28
Hidden size	1024
Intermediate size	3072
Attention heads	16 (8 KV heads, GQA)
Head dim	128
Vocab size	151936
Max sequence length	4096
Attention	parallax (`attn_type="parallax"`)
Tokenizer	Qwen3

Usage

The model ships custom modeling code, so load it with trust_remote_code=True (requires a recent transformers with Qwen3 support):

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "YifeiZuo/Parallax-0.6B"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)

prompt = "The quick brown fox"
ids = tok(prompt, return_tensors="pt").input_ids
out = model.generate(ids, max_new_tokens=32)
print(tok.decode(out[0], skip_special_tokens=True))

License

Released under the Apache 2.0 license.

Downloads last month: 8

Safetensors

Model size

0.7B params

Tensor type

BF16

Collection including YifeiZuo/Parallax-0.6B

Parallax-Experiment

Collection

Experimental Parallax (Parameterized Local Linear Attention) models. • 2 items • Updated Jun 10

Paper for YifeiZuo/Parallax-0.6B

Parallax: Parameterized Local Linear Attention for Language Modeling

Paper • 2605.29157 • Published May 27 • 11