ToPo-ToPo/diffusiongemma-26B-A4B-it-mlx-bf16
MLX bf16 conversion of google/diffusiongemma-26B-A4B-it (mlx-vlm).
Block-diffusion LM built on Gemma 4 (25.2B total / 3.8B active, MoE 128+1 experts, vision).
Provenance (self-converted)
- Source:
google/diffusiongemma-26B-A4B-it(license: apache-2.0) - Tool: mlx-vlm 0.6.9
mlx_vlm.convert(no quantization (format conversion only)), ~16 bpw model_type: diffusion_gemmais supported natively by mlx-vlm 0.6.9; no patch needed.chat_template.jinjais not the base repo's copy: it is the patched Gemma 4 Canonical Chat Template fromToPo-ToPo/gemma-4-26B-A4B-it-mlx-4bit, which suppresses the thinking channel whenenable_thinkingis false (otherwise the literal wordthoughtleaks into the answer). Thinking is off by default. Weights are unaffected — restore the base repo's template for stock behaviour.
Usage
from mlx_vlm import load
model, processor = load("ToPo-ToPo/diffusiongemma-26B-A4B-it-mlx-bf16")
Diffusion generation takes its own flags:
python -m mlx_vlm generate --model ToPo-ToPo/diffusiongemma-26B-A4B-it-mlx-bf16 \
--prompt "Why is the sky blue?" \
--max-tokens 256 --max-denoising-steps 48 --diffusion-sampler entropy-bound