Diffusiongemma 26B A4B It HERETIC Uncensored 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 14 quants, from 8.6 GB (TQ1_0) to 50.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Diffusiongemma 26B A4B It HERETIC Uncensored – a 26.3B parameter diffusion model
Diffusiongemma 26B A4B It HERETIC Uncensored is a 26.3B parameter diffusion model with 4B active MoE experts. It uses a block‑diffusion architecture and is released under Apache‑2.0. The model is quantized for use with llama.cpp.
Good at
- Large context generation
- MoE expert handling
- Diffusion‑based text generation
Limits
- No vision support
- Requires custom loading class
- Large VRAM for higher quant
Best for
- Research on diffusion models
- Testing MoE behavior
- Generating long‑form text
Who it’s for. Researchers and developers who need a large diffusion‑based language model and are comfortable with custom loading and quantization. The model is suitable for experimentation rather than production use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 8.6 GB | 17.1 GB | Too big | Get file → | |
| TQ2_0 | 9.4 GB | 17.9 GB | Too big | Get file → | |
| Q2_K | 10.6 GB | 19.1 GB | Too big | Get file → | |
| IQ3_S | 12.2 GB | 20.8 GB | Too big | Get file → | |
| IQ3_M | 12.4 GB | 21.0 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 21.8 GB | Too big | Get file → | |
| IQ4_XS | 14.1 GB | 22.6 GB | Too big | Get file → | |
| IQ4_NL | 14.6 GB | 23.1 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 25.4 GB | Too big | Get file → | |
| Q5_K_M | 19.1 GB | 27.7 GB | Too big | Get file → | |
| Q6_K | 22.7 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 35.4 GB | Too big | Get file → | |
| BF16 | 50.5 GB | 59.1 GB | Too big | Get file → | |
| — | 50.5 GB | 59.1 GB | Too big | Get file → |
For 8‑GB VRAM use TQ1_0 (8.58 GB). For 12‑GB VRAM use TQ2_0 (9.36 GB). For 16‑GB VRAM use Q2_K (10.59 GB). Larger VRAM allows higher‑quality quants such as Q4_K_M (16.81 GB).
What GPU do you need for Diffusiongemma 26B A4B It HERETIC Uncensored?
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: the best quant that fits is IQ4_NL (14.6 GB file, about 23.1 GB in use).
- 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 HERETIC Uncensored quant should you choose?
Q4_K_M is the usual starting point for Diffusiongemma 26B A4B It HERETIC Uncensored: 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.
If memory is tight, the smallest file is TQ1_0 at 8.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Diffusiongemma 26B A4B It HERETIC Uncensored
How much VRAM does Diffusiongemma 26B A4B It HERETIC Uncensored 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 HERETIC Uncensored on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Diffusiongemma 26B A4B It HERETIC Uncensored GGUF?
It depends on the quant: TQ1_0 is 8.6 GB, TQ2_0 is 9.4 GB, Q2_K is 10.6 GB, IQ3_S is 12.2 GB, IQ3_M is 12.4 GB, Q3_K_M is 13.3 GB and 8 more.
What context length does Diffusiongemma 26B A4B It HERETIC Uncensored 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 HERETIC Uncensored GGUF?
The files are on Hugging Face in the yabaimimi/edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-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 HERETIC Uncensored 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 this model on 8 GB VRAM?
Yes, use the TQ1_0 quant which is 8.58 GB and requires about 17.1 GB of VRAM at 8k context.
Does the model support vision input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.