SU

SuperGemma4-31b-abliterated

SupergemmaGGUF by JiunsongUpdated 2026-04-15
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant18.7 GB
Quick answer

SuperGemma4-31b-abliterated needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

SuperGemma4-31b-abliterated – a 31B uncensored Gemma 4 model for local use

SuperGemma4-31b-abliterated is a 30.7B parameter Gemma 4 model released in GGUF format. It offers uncensored chat, strong coding help, and sharp reasoning. The model is optimized for local deployment with llama.cpp and similar runtimes.

Good at

  • Uncensored chat
  • Coding and debugging
  • Reasoning and planning

Limits

  • No vision support
  • Requires large VRAM
  • License: gemma

Best for

  • Local chat assistants
  • Code generation
  • Technical troubleshooting

Who it’s for. Developers and power users who need a local, uncensored Gemma 4 experience with strong coding and reasoning capabilities. The model is suitable for those who prefer a lightweight deployment path for a 31B model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M18.7 GB 51.4 GB
Too big Get file →

The Q4_K_M quant file is 18.69 GB and requires approximately 51.4 GB of VRAM at 8 k context. This is the only quant available, so use it if your GPU can accommodate the memory estimate. For smaller GPUs, a different quant is not provided.

What GPU do you need for SuperGemma4-31b-abliterated?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which SuperGemma4-31b-abliterated quant should you choose?

Q4_K_M is the usual starting point for SuperGemma4-31b-abliterated: it balances file size and quality well. Here it is a 18.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byJiunsong
Licensegemma
Downloads (HF)901
Last updated2026-04-15

Frequently asked questions about SuperGemma4-31b-abliterated

How much VRAM does SuperGemma4-31b-abliterated need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 SuperGemma4-31b-abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 51.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SuperGemma4-31b-abliterated GGUF?

It depends on the quant: Q4_K_M is 18.7 GB.

What context length does SuperGemma4-31b-abliterated support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download SuperGemma4-31b-abliterated GGUF?

The files are on Hugging Face in the Jiunsong/SuperGemma4-31b-abliterated-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 SuperGemma4-31b-abliterated 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?

No. The Q4_K_M quant requires about 51.4 GB of VRAM at 8 k context, which exceeds 8 GB.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is licensed under the gemma license.

Similar models

Browse all →

More from Jiunsong

All by Jiunsong →

More Supergemma models

All Supergemma →

Other medium models

All medium models →