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_gemma is supported natively by mlx-vlm 0.6.9; no patch needed.
  • chat_template.jinja is not the base repo's copy: it is the patched Gemma 4 Canonical Chat Template from ToPo-ToPo/gemma-4-26B-A4B-it-mlx-4bit, which suppresses the thinking channel when enable_thinking is false (otherwise the literal word thought leaks into the answer). Thinking is off by default. Weights are unaffected β€” 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
Downloads last month
46
Safetensors
Model size
26B params
Tensor type
BF16
Β·
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for ToPo-ToPo/diffusiongemma-26B-A4B-it-mlx-bf16

Finetuned
(39)
this model