Text Generation
MLX
Safetensors
gemma3
4-bit precision
4bit
apple-silicon
chat
conversational
edge-ai
function-calling
gemma
gemma-3
google
google-gemma
instruct
local-llm
m1
m2
m3
m4
mac
mac-mini
mac-studio
macbook-air
macbook-pro
macos
metal
mlx-community
mlx-lm
no-cloud
offline
on-device
outlier
outlier-app
private
private-ai
quantized
tool-use
Instructions to use Outlier-Ai/gemma-3-27b-it-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Outlier-Ai/gemma-3-27b-it-MLX-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Outlier-Ai/gemma-3-27b-it-MLX-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use Outlier-Ai/gemma-3-27b-it-MLX-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Outlier-Ai/gemma-3-27b-it-MLX-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Outlier-Ai/gemma-3-27b-it-MLX-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Outlier-Ai/gemma-3-27b-it-MLX-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 255999, | |
| "eoi_token_index": 256000, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "mm_tokens_per_image": 256, | |
| "model_type": "gemma3", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "text_config": { | |
| "head_dim": 128, | |
| "hidden_size": 5376, | |
| "intermediate_size": 21504, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 62, | |
| "num_key_value_heads": 16, | |
| "query_pre_attn_scalar": 168, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "sliding_window": 1024, | |
| "vocab_size": 262208 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.0.dev0" | |
| } |