Qwen3-4B-MLX-4bit

76.9K
16
66K
Extended context
4.0B
1 language
license:apache-2.0
by
Qwen
Language Model
OTHER
4B params
Fair
77K downloads
Community-tested
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
9GB+ RAM
Mobile
Laptop
Server
Quick Summary

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
4GB+ RAM

Code Examples

bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
bash
pip install --upgrade transformers mlx_lm
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)
python
from mlx_lm import load, generate

model, tokenizer = load("Qwen/Qwen3-4B-MLX-4bit")
prompt = "Hello, please introduce yourself and tell me what you can do."

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

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    verbose=True,
    max_tokens=1024
)

print(response)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.