GE

gemini 3.1 pro distill reasoning 12B QKVO

GeminiGGUF by mfielding92Updated 2026-02-20
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant12.5 GB
Quick answer

gemini 3.1 pro distill reasoning 12B QKVO needs about 16.2 GB of memory at its main file (a 12.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

gemini 3.1 pro distill reasoning 12B QKVO is a 11.8B-parameter Gemini model in GGUF format, quantized by mfielding92. Its trained context length is 128K tokens. The repository has 1 quant file, from 12.5 GB to 12.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.5 GB 16.2 GB
Too big Get file →

What GPU do you need for gemini 3.1 pro distill reasoning 12B QKVO?

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 the main file (12.5 GB file, about 16.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymfielding92
FamilyGemini
Licenseapache-2.0
Downloads (HF)74
Last updated2026-02-20

Frequently asked questions about gemini 3.1 pro distill reasoning 12B QKVO

How much VRAM does gemini 3.1 pro distill reasoning 12B QKVO need?

About 16.2 GB at its main file with an 8K context window. That is the 12.5 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 gemini 3.1 pro distill reasoning 12B QKVO on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemini 3.1 pro distill reasoning 12B QKVO GGUF?

It depends on the quant: file is 12.5 GB.

What context length does gemini 3.1 pro distill reasoning 12B QKVO support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download gemini 3.1 pro distill reasoning 12B QKVO GGUF?

The files are on Hugging Face in the mfielding92/gemini-3.1-pro-distill-reasoning-12B-QKVO-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 gemini 3.1 pro distill reasoning 12B QKVO 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.

Similar models

Browse all →

More from mfielding92

All by mfielding92 →

More Gemini models

All Gemini →

Other medium models

All medium models →