Qwen2.5-Coder-32B-Instruct-4bit

152
10
license:apache-2.0
by
mlx-community
Language Model
OTHER
32B params
New
152 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
72GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
30GB+ RAM

Code Examples

Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxbash
pip install mlx-lm
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)
Use with mlxpython
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-4bit")

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)

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.