GE

Gemma 4 31b RP MERGE NVFP4 BF16

GemmaGGUF by Rada2025Updated 2026-09-11
Download on Hugging Face
Parameters10B
Context256K
Layers60
Architecturegemma4
Smallest quant20.5 GB
Quick answer

Gemma 4 31b RP MERGE NVFP4 BF16 needs about 53.2 GB of memory at BF16 (a 20.5 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.

Gemma 4 31b RP MERGE NVFP4 BF16 is a 10B-parameter Gemma model in GGUF format, quantized by Rada2025. Its trained context length is 256K tokens. The repository has 1 quant file, from 20.5 GB (BF16) to 20.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1620.5 GB 53.2 GB
Too big Get file →

What GPU do you need for Gemma 4 31b RP MERGE NVFP4 BF16?

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 Gemma 4 31b RP MERGE NVFP4 BF16 quant should you choose?

BF16 (20.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters10B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byRada2025
FamilyGemma
Licenseapache-2.0
Downloads (HF)134
Last updated2026-09-11

Frequently asked questions about Gemma 4 31b RP MERGE NVFP4 BF16

How much VRAM does Gemma 4 31b RP MERGE NVFP4 BF16 need?

About 53.2 GB at BF16 with an 8K context window. That is the 20.5 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 RP MERGE NVFP4 BF16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 53.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 31b RP MERGE NVFP4 BF16 GGUF?

It depends on the quant: BF16 is 20.5 GB.

What context length does Gemma 4 31b RP MERGE NVFP4 BF16 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 RP MERGE NVFP4 BF16 GGUF?

The files are on Hugging Face in the Rada2025/Gemma-4-31b-RP-MERGE-NVFP4-BF16-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 RP MERGE NVFP4 BF16 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.

Other GGUFs of Giftige-Blume-31B-v1-StyleSwap

Similar models

Browse all →

More Gemma models

All Gemma →

Other medium models

All medium models →