Hugging Face's logo

safwanahmadkhan
/
gemma-4-12B-it-DFlash-8bit-mlx-fp16

Text Generation
MLX
Safetensors
qwen3
fp16
8bit
quantized
Model card Files
xet
 Community
How to use from the
Use from the
MLX library
# 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("safwanahmadkhan/gemma-4-12B-it-DFlash-8bit-mlx-fp16")

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

Model Card for Model ID

This is FP16 precision for use with M1/M2 chips. These lack the default BF16 precision which is originally used in the base model

Downloads last month
96
Safetensors
Model size
0.7B params
Tensor type
F16
·
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for safwanahmadkhan/gemma-4-12B-it-DFlash-8bit-mlx-fp16

Base model

z-lab/gemma4-12B-it-DFlash
Finetuned
(2)
this model