GE

UNSEEN Gemma 4 26B NSFW

GemmaGGUF by JommarnUpdated 2026-09-01
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant10.4 GB
Quick answer

UNSEEN Gemma 4 26B NSFW needs about 25.3 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 7 quants, from 10.4 GB (IQ2_M) to 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

UNSEEN Gemma‑4‑26B NSFW – a 27‑billion‑parameter vision‑enabled LLM in GGUF format

UNSEEN Gemma‑4‑26B NSFW is a 27‑billion‑parameter model with vision capability. It is available in multiple quantized GGUF formats for efficient deployment on consumer GPUs and Apple Silicon. The model is hosted on the Jommarn repository and requires a separate vision projector for image understanding.

Good at

  • Vision‑enabled text generation
  • Large context handling (262,144 tokens)
  • High‑capacity multimodal tasks

Limits

  • No license information provided
  • Requires separate mmproj for vision
  • Large VRAM needed for higher‑bit quantizations

Best for

  • Multimodal content creation
  • Large‑scale text and image inference
  • Research on vision‑enabled LLMs

Who it’s for. Developers and researchers needing a high‑capacity vision‑enabled LLM that can be run on consumer GPUs with GGUF quantization. The model is suitable for applications that require extensive context and multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M10.4 GB 18.9 GB
Too big Get file →
IQ3_M12.4 GB 20.9 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.6 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 8–10 GB VRAM, use IQ2_M (10.38 GB). For 12–14 GB VRAM, use IQ3_M (12.39 GB). For 16–18 GB VRAM, use Q4_K_M (16.8 GB). Higher‑bit quants provide better quality at the cost of VRAM.

What GPU do you need for UNSEEN Gemma 4 26B NSFW?

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 IQ3_M (12.4 GB file, about 20.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.6 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 UNSEEN Gemma 4 26B NSFW quant should you choose?

Q4_K_M is the usual starting point for UNSEEN Gemma 4 26B NSFW: 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 IQ2_M at 10.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters25.2B (approximate, mixture of experts)
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byJommarn
FamilyGemma
Downloads (HF)25,456
Last updated2026-09-01

Frequently asked questions about UNSEEN Gemma 4 26B NSFW

How much VRAM does UNSEEN Gemma 4 26B NSFW need?

About 25.3 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 UNSEEN Gemma 4 26B NSFW on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of UNSEEN Gemma 4 26B NSFW GGUF?

It depends on the quant: IQ2_M is 10.4 GB, IQ3_M is 12.4 GB, Q4_K_M is 16.8 GB, Q5_K_M is 19.1 GB, Q6_K is 22.6 GB, Q8_0 is 26.9 GB and 1 more.

What context length does UNSEEN Gemma 4 26B NSFW 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 UNSEEN Gemma 4 26B NSFW GGUF?

The files are on Hugging Face in the Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run UNSEEN Gemma‑4‑26B NSFW on an RTX 3060 12GB?

Yes, using IQ2_M quantization (~10.38 GB) will fit within 12 GB VRAM with some overhead.

Do I need a separate file for image understanding?

Yes, download mmproj-gemma4-vision-f16.gguf and pass it with --mmproj to enable vision.

What is the approximate memory usage at 8k context for Q4_K_M?

About 25.3 GB of VRAM is estimated for Q4_K_M at 8k context.

Similar models

Browse all →

More Gemma models

All Gemma →

Other medium models

All medium models →