GE

Gemma 4 31B StyleTune

GemmaGGUF by mradermacherUpdated 2026-07-04
Download on Hugging Face
Parameters32.1B
Context256K
Layers60
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Gemma 4 31B StyleTune needs about 52.2 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.0 GB to 26.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma 4 31B StyleTune – a single‑tensor style‑finetuned Gemma 4 model

Gemma 4 31B StyleTune is a 31‑billion‑parameter Gemma model that has been finetuned by modifying only the lm_head tensor. The change reduces clichés and alters the writing style while keeping all other capabilities intact. It is available in multiple GGUF quantizations.

Good at

  • Reduced clichés in narrative text
  • Targeted style change with minimal training
  • Retains full reasoning and instruction following

Limits

  • Requires large VRAM for full model (≈32–59 GB at 8k context)
  • No vision support
  • Apache‑2.0 license restricts commercial redistribution

Best for

  • Narrative generation with a distinct voice
  • Role‑play scenarios needing a fresh style
  • Testing style‑tuning techniques on large models

Who it’s for. Developers and researchers who want to experiment with style‑finetuning on a large Gemma model without retraining all layers. The model is suitable for those who can provide the necessary GPU memory for inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 32.7 GB
Too big Get file →
IQ1_S7.6 GB 40.3 GB
Too big Get file →
IQ1_M8.2 GB 40.9 GB
Too big Get file →
IQ2_XXS9.1 GB 41.8 GB
Too big Get file →
IQ2_XS10.0 GB 42.7 GB
Too big Get file →
IQ2_S10.8 GB 43.5 GB
Too big Get file →
Q2_K_S11.4 GB 44.2 GB
Too big Get file →
IQ2_M11.5 GB 44.2 GB
Too big Get file →
Q2_K12.4 GB 45.1 GB
Too big Get file →
IQ3_XXS12.7 GB 45.4 GB
Too big Get file →
IQ3_XS13.7 GB 46.4 GB
Too big Get file →
IQ3_S14.4 GB 47.1 GB
Too big Get file →
Q3_K_S14.4 GB 47.1 GB
Too big Get file →
IQ3_M15.0 GB 47.7 GB
Too big Get file →
Q3_K_M15.9 GB 48.6 GB
Too big Get file →
Q3_K_L17.2 GB 49.9 GB
Too big Get file →
IQ4_XS17.5 GB 50.2 GB
Too big Get file →
Q4_018.5 GB 51.2 GB
Too big Get file →
Q4_K_S18.6 GB 51.3 GB
Too big Get file →
Q4_K_M19.5 GB 52.2 GB
Too big Get file →
Q4_120.4 GB 53.1 GB
Too big Get file →
Q5_K_S22.3 GB 55.0 GB
Too big Get file →
Q5_K_M22.8 GB 55.5 GB
Too big Get file →
Q6_K26.4 GB 59.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (≈51 GB memory at 8k context). For 12 GB VRAM use Q4_K_M (≈52 GB). For 16 GB VRAM use Q5_K_S (≈55 GB). Memory estimates are approximate and based on the provided file sizes.

What GPU do you need for Gemma 4 31B StyleTune?

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: the best quant that fits is IQ3_M (15.0 GB file, about 47.7 GB in use).

Which Gemma 4 31B StyleTune quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 31B StyleTune: it balances file size and quality well. Here it is a 19.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters32.1B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licenseapache-2.0
Downloads (HF)4,196
Last updated2026-07-04

Frequently asked questions about Gemma 4 31B StyleTune

How much VRAM does Gemma 4 31B StyleTune need?

About 52.2 GB at Q4_K_M with an 8K context window. That is the 19.5 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 31B StyleTune on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 31B StyleTune GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.6 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.1 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.8 GB and 18 more.

What context length does Gemma 4 31B StyleTune 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 Gemma 4 31B StyleTune GGUF?

The files are on Hugging Face in the mradermacher/Gemma-4-31B-StyleTune-i1-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 Gemma 4 31B StyleTune 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 Gemma 4 31B StyleTune on 8 GB VRAM?

No, the smallest quant requires about 32 GB VRAM at 8k context. Even the lightest quant is too large for 8 GB.

Does this model support vision inputs?

No, the model is purely text and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Gemma-4-31B-StyleTune

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →