⚡ All JANG models are meant to be run in vMLX

Gemma-4-26B-A4B-it-JANG_4M

JANG-quantized Gemma-4 MoE for Apple Silicon. Created by Jinho Jang — eric@jangq.ai.

See the full JANGQ-AI collection for all profiles.

Loading

from mlx_lm import load, generate
model, tokenizer = load("JANGQ-AI/Gemma-4-26B-A4B-it-JANG_4M")
print(generate(model, tokenizer, "Hello", max_tokens=256))

Stock mlx_lm picks up the multi-stop-token list ([1, 106, 50]) automatically from generation_config.json — no manual configuration required.