QwQ-Coder-R1-Distill-32B-mlx-3Bit

Name: QwQ-Coder-R1-Distill-32B-mlx-3Bit
Author: tomasmcm

32.0B

1 language

—

tomasmcm

Language Model

OTHER

32B params

New

1 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

72GB+ RAM

Mobile

Laptop

Server

Quick Summary

The Model tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit was converted to MLX format from tomasmcm/QwQ-Coder-R1-Distill-32B using mlx-lm version 0.

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 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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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("tomasmcm/QwQ-Coder-R1-Distill-32B-mlx-3Bit")

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.