Instructions to use huseyincavus/gemma-3-270m-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use huseyincavus/gemma-3-270m-4bit-mlx 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("huseyincavus/gemma-3-270m-4bit-mlx") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use huseyincavus/gemma-3-270m-4bit-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "huseyincavus/gemma-3-270m-4bit-mlx" --prompt "Once upon a time"
- Atomic Chat
Download generation_config.json from huseyincavus/gemma-3-270m-4bit-mlx: direct link, hf CLI and curl.
- Browser
- Download file 133 Bytes
-
https://huggingface.co/huseyincavus/gemma-3-270m-4bit-mlx/resolve/main/generation_config.json
- Command line
-
hf download hf://huseyincavus/gemma-3-270m-4bit-mlx/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/huseyincavus/gemma-3-270m-4bit-mlx/resolve/main/generation_config.json
133 Bytes
| { | |
| "cache_implementation": "hybrid", | |
| "do_sample": true, | |
| "top_k": 64, | |
| "top_p": 0.95, | |
| "transformers_version": "4.55.0.dev0" | |
| } | |