Instructions to use mlx-community/gemma-2-27b-bf16-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gemma-2-27b-bf16-8bit with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/gemma-2-27b-bf16-8bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/gemma-2-27b-bf16-8bit")
model = AutoModelForCausalLM.from_pretrained("mlx-community/gemma-2-27b-bf16-8bit", device_map="auto")

MLX

How to use mlx-community/gemma-2-27b-bf16-8bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

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

model, tokenizer = load("mlx-community/gemma-2-27b-bf16-8bit")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/gemma-2-27b-bf16-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/gemma-2-27b-bf16-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/gemma-2-27b-bf16-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/gemma-2-27b-bf16-8bit

SGLang

How to use mlx-community/gemma-2-27b-bf16-8bit 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 "mlx-community/gemma-2-27b-bf16-8bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/gemma-2-27b-bf16-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mlx-community/gemma-2-27b-bf16-8bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/gemma-2-27b-bf16-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use mlx-community/gemma-2-27b-bf16-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "mlx-community/gemma-2-27b-bf16-8bit" --prompt "Once upon a time"

Docker Model Runner
How to use mlx-community/gemma-2-27b-bf16-8bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/gemma-2-27b-bf16-8bit
```
Atomic Chat

gemma-2-27b-bf16-8bit / README.md

awni

Upload folder using huggingface_hub (#1)

1bb540c verified almost 2 years ago

preview code

Raw History Blame Contribute Delete

1.22 kB

metadata

base_model: google/gemma-2-27b
library_name: transformers
license: gemma
pipeline_tag: text-generation
tags:
  - mlx
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
  To access Gemma on Hugging Face, you’re required to review and agree to
  Google’s usage license. To do this, please ensure you’re logged in to Hugging
  Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license

mlx-community/gemma-2-27b-8-bit

The Model mlx-community/gemma-2-27b-8-bit was converted to MLX format from google/gemma-2-27b using mlx-lm version 0.19.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-27b-8-bit")

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)