edwixx·Gemma·DiffusionGemmaForBlockDiffusion

Diffusiongemma 26B A4B IT HERETIC Uncensored — Hardware Requirements & GPU Compatibility

Chat

Diffusiongemma 26B A4B IT HERETIC Uncensored is a 25.8B-parameter open language model from edwixx in the Gemma family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 52.29 GB of VRAM — see which GPUs and Macs can run it below.

13 downloads 3 likes262K context

Specifications

Publisher
edwixx
Family
Gemma
Parameters
25.8B
Architecture
DiffusionGemmaForBlockDiffusion
Context Length
262,144 tokens
Vocabulary Size
262,144
Release Date
2026-06-11
License
Apache 2.0

Get Started

How Much VRAM Does Diffusiongemma 26B A4B IT HERETIC Uncensored Need?

Select a quantization to see compatible GPUs below.

QuantizationBitsVRAM
BF16est.16.0052.3 GB

est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.

Which GPUs Can Run Diffusiongemma 26B A4B IT HERETIC Uncensored?

BF16 · 52.3 GB

Diffusiongemma 26B A4B IT HERETIC Uncensored (BF16) requires 52.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 68+ GB is recommended. Using the full 262K context window can add up to 43.9 GB, bringing total usage to 96.2 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.

Which Devices Can Run Diffusiongemma 26B A4B IT HERETIC Uncensored?

BF16 · 52.3 GB

8 devices with unified memory can run Diffusiongemma 26B A4B IT HERETIC Uncensored, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).

Related Models

Frequently Asked Questions

How much VRAM does Diffusiongemma 26B A4B IT HERETIC Uncensored need?

Diffusiongemma 26B A4B IT HERETIC Uncensored requires 52.3 GB of VRAM at BF16. Full 262K context adds up to 43.9 GB (96.2 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 25.8B × 16 bits ÷ 8 = 51.6 GB

KV Cache + Overhead 0.7 GB (at 2K context + ~0.3 GB framework)

KV Cache + Overhead 44.6 GB (at full 262K context)

VRAM usage by quantization

52.3 GB
96.2 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run Diffusiongemma 26B A4B IT HERETIC Uncensored?

No — Diffusiongemma 26B A4B IT HERETIC Uncensored requires at least 52.3 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

Can I run Diffusiongemma 26B A4B IT HERETIC Uncensored on a Mac?

Diffusiongemma 26B A4B IT HERETIC Uncensored requires at least 52.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run Diffusiongemma 26B A4B IT HERETIC Uncensored locally?

Yes — Diffusiongemma 26B A4B IT HERETIC Uncensored can run locally on consumer hardware. At BF16 quantization it needs 52.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Diffusiongemma 26B A4B IT HERETIC Uncensored?

At BF16, Diffusiongemma 26B A4B IT HERETIC Uncensored can reach ~56 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: AMD Instinct MI300X5300 ÷ 52.3 × 0.55 = ~56 tok/s

Estimated speed at BF16 (52.3 GB)

~56 tok/s
~42 tok/s
~35 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Diffusiongemma 26B A4B IT HERETIC Uncensored?

At BF16, the download is about 51.65 GB.

Which GPUs can run Diffusiongemma 26B A4B IT HERETIC Uncensored?

No single consumer GPU has enough VRAM to run Diffusiongemma 26B A4B IT HERETIC Uncensored at BF16 (52.3 GB). Multi-GPU or professional hardware is required.

Which devices can run Diffusiongemma 26B A4B IT HERETIC Uncensored?

8 devices with unified memory can run Diffusiongemma 26B A4B IT HERETIC Uncensored at BF16 (52.3 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), Mac Studio M4 Max (64 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.