GE

SPARK2

GemmaGGUF by kistepAIUpdated 2026-08-06
Download on Hugging Face
Parameters27B
Context128K
Layers—
Architecturegemma3
Smallest quant25.7 GB
Quick answer

SPARK2 needs about 29.3 GB of memory at BF16 (a 25.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 25.7 GB (BF16) to 28.3 GB (BF16).

SPARK2 is a 27B-parameter Gemma model in GGUF format, quantized by kistepAI. Its trained context length is 128K tokens. The repository has 2 quant files, from 25.7 GB (BF16) to 28.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1625.7 GB 29.3 GB
Too big Get file →
BF1628.3 GB 32.2 GB
Too big Get file →

What GPU do you need for SPARK2?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is BF16 (25.7 GB file, about 29.3 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (28.3 GB file, about 32.2 GB in use).

Which SPARK2 quant should you choose?

BF16 (25.7 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

Architecturegemma3
Parameters27B
Trained context131,072 tokens

Source

Quantized bykistepAI
FamilyGemma
RepositorykistepAI/SPARK2
Downloads (HF)0
Last updated2026-08-06

Frequently asked questions about SPARK2

How much VRAM does SPARK2 need?

About 29.3 GB at BF16 with an 8K context window. That is the 25.7 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 SPARK2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SPARK2 GGUF?

It depends on the quant: BF16 is 25.7 GB, BF16 is 28.3 GB.

What context length does SPARK2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download SPARK2 GGUF?

The files are on Hugging Face in the kistepAI/SPARK2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of gemma-3-27b-it

Similar models

Browse all →

More from kistepAI

All by kistepAI →

More Gemma models

All Gemma →

Other medium models

All medium models →