DI

diffusiongemma 26B A4B it

DiffusiongemmaGGUF by unslothUpdated 2026-07-04
Download on Hugging Face
Parameters25.3B
Context256K
Layers30
Architecturediffusion-gemma
Smallest quant16.8 GB
Quick answer

diffusiongemma 26B A4B it needs about 25.4 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 16.8 GB (Q4_K_M) to 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

DiffusionGemma 26B A4B it – multimodal text generation with block‑diffusion

DiffusionGemma 26B A4B it is a 27‑billion‑parameter multimodal model that uses discrete diffusion to generate text. It supports text, image, and video inputs and is optimized for low‑latency inference on a single accelerator. The model is released under Apache 2.0.

Good at

  • Fast block‑diffusion decoding
  • Multimodal input handling
  • Reasoning with MoE

Limits

  • Requires custom llama.cpp branch
  • Large VRAM for higher context
  • No native vision support in standard llama.cpp

Best for

  • Fast text generation from images
  • Low‑latency inference on single GPU
  • Reasoning tasks with multimodal prompts

Who it’s for. Developers building local inference pipelines that need fast, multimodal text generation. Researchers interested in MoE efficiency and block‑diffusion decoding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.8 GB 25.4 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.7 GB 31.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →
BF1650.5 GB 59.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (16.81 GB file, ~25.4 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (19.15 GB file, ~27.7 GB memory). For 16 GB VRAM, Q6_K (22.65 GB file, ~31.2 GB memory).

What GPU do you need for diffusiongemma 26B A4B it?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q6_K (22.7 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which diffusiongemma 26B A4B it quant should you choose?

Q4_K_M is the usual starting point for diffusiongemma 26B A4B it: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 26.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturediffusion-gemma
Parameters25.3B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byunsloth
Licenseapache-2.0
Downloads (HF)37,710
Last updated2026-07-04

Frequently asked questions about diffusiongemma 26B A4B it

How much VRAM does diffusiongemma 26B A4B it need?

About 25.4 GB at Q4_K_M with an 8K context window. That is the 16.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run diffusiongemma 26B A4B it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of diffusiongemma 26B A4B it GGUF?

It depends on the quant: Q4_K_M is 16.8 GB, Q5_K_M is 19.1 GB, Q6_K is 22.7 GB, Q8_0 is 26.9 GB, BF16 is 50.5 GB.

What context length does diffusiongemma 26B A4B it support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download diffusiongemma 26B A4B it GGUF?

The files are on Hugging Face in the unsloth/diffusiongemma-26B-A4B-it-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does diffusiongemma 26B A4B it use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run DiffusionGemma on 8 GB VRAM?

Yes, using the Q4_K_M quantized file. It requires about 25.4 GB of VRAM at 8 k context, so you need to reduce context or use offloading.

Does this model support image input?

Yes, DiffusionGemma can process images with variable aspect ratio and resolution.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of diffusiongemma-26B-A4B-it

Similar models

Browse all →

More from unsloth

All by unsloth →

More Diffusiongemma models

All Diffusiongemma →

Other medium models

All medium models →