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 model.safetensors from huseyincavus/gemma-3-270m-4bit-mlx: direct link, hf CLI and curl.
- Browser
- Download file 143 MB
-
https://huggingface.co/huseyincavus/gemma-3-270m-4bit-mlx/resolve/main/model.safetensors
- Command line
-
hf download hf://huseyincavus/gemma-3-270m-4bit-mlx/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/huseyincavus/gemma-3-270m-4bit-mlx/resolve/main/model.safetensors
143 MB
- Xet hash:
- 286cf308d75f32942e022f4578c97226270da0de279b952ac9a3a717645214b1
- Size of remote file:
- 143 MB
- SHA256:
- 6f5198486410c72e39bfe1a6400d424a16d58b6991a638be1e4f8abff8b9e59d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.