GE

Gemma-4-12B-OBLITERATED-v2

GemmaGGUF by Mal1ccUpdated 2026-10-06
Download on Hugging Face
Parameters11.9B
Context128K
Layers48
Architecturegemma4
Smallest quant7.4 GB
Quick answer

Gemma-4-12B-OBLITERATED-v2 needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 7.4 GB (Q4_K_M) to 23.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Gemma‑4‑12B‑OBLITERATED‑v2 – an 11.9B‑parameter multimodal model with zero refusal

Gemma‑4‑12B‑OBLITERATED‑v2 is a 11.9B‑parameter model from the Gemma family. It supports text, image, audio, and video inputs and outputs text. The model is optimized for local execution and has a 131072‑token context window.

Good at

  • Multimodal reasoning
  • Native function‑calling
  • Zero refusal

Limits

  • No vision support in quantized form
  • Large VRAM requirement for higher precision
  • Research‑only license

Best for

  • Alignment research
  • Red‑team safety testing
  • Local‑first AI experimentation

Who it’s for. This model is intended for alignment researchers, red‑teamers, and AI safety evaluators who need an unrestricted baseline for benchmarking. It is not suitable for general content generation or commercial deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.4 GB 20.8 GB
Too big Get file →
Q8_012.7 GB 26.1 GB
Too big Get file →
BF1623.8 GB 37.2 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (7.38 GB, ~20.8 GB memory at 8k context). For 12 GB VRAM use Q8_0 (12.67 GB, ~26.1 GB memory). BF16 requires 23.83 GB and ~37.2 GB memory, suitable only for high‑end servers.

What GPU do you need for Gemma-4-12B-OBLITERATED-v2?

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 Q4_K_M (7.4 GB file, about 20.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 37.2 GB in use).

Which Gemma-4-12B-OBLITERATED-v2 quant should you choose?

Q4_K_M is the usual starting point for Gemma-4-12B-OBLITERATED-v2: it balances file size and quality well. Here it is a 7.4 GB file.

The Q8_0 file is 12.7 GB, about 1.7 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

Architecturegemma4
Parameters11.9B
Layers48
Trained context131,072 tokens
KV cache (fp16)1536 KB per token

Source

Quantized byMal1cc
FamilyGemma
Licensegemma
Downloads (HF)985
Last updated2026-10-06

Frequently asked questions about Gemma-4-12B-OBLITERATED-v2

How much VRAM does Gemma-4-12B-OBLITERATED-v2 need?

About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Gemma-4-12B-OBLITERATED-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma-4-12B-OBLITERATED-v2 GGUF?

It depends on the quant: Q4_K_M is 7.4 GB, Q8_0 is 12.7 GB, BF16 is 23.8 GB.

What context length does Gemma-4-12B-OBLITERATED-v2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download Gemma-4-12B-OBLITERATED-v2 GGUF?

The files are on Hugging Face in the Mal1cc/Gemma-4-12B-OBLITERATED repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Gemma-4-12B-OBLITERATED-v2 use?

Hugging Face lists the license as gemma. 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?

Use the Q4_K_M quantized file (7.38 GB). It requires about 20.8 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision?

The model has vision capabilities, but the quantized GGUF files do not include a separate vision encoder. Vision input is handled natively in the unified model.

Is this model safe for general use?

No. The safety guardrails have been surgically removed for research purposes. It is intended only for alignment research and red‑team testing.

Other GGUFs of gemma-4-12B-it

Similar models

Browse all →

More from Mal1cc

All by Mal1cc →

More Gemma models

All Gemma →

Other medium models

All medium models →