gemma-4-E4B-RotorQuant-GGUF-Q2_K

GGUF Q2_K weight-quantized variant of google/gemma-4-E4B with RotorQuant KV cache compression for efficient inference with llama.cpp, Ollama, and LM Studio.

Overview

This model combines two compression techniques:

• GGUF Q2_K weight quantization — reduces model size from ~8GB to ~2 GB
• RotorQuant KV cache compression — block-diagonal rotations (Clifford algebra) for 3-bit KV cache, 5.3x faster prefill

Quickstart

llama.cpp

llama-cli -m gemma-4-E4B-RotorQuant-GGUF-Q2_K.gguf \
  --cache-type-k planar3 --cache-type-v iso3 \
  -p "Explain quantum computing"

Ollama

ollama run majentik/gemma-4-E4B-RotorQuant-GGUF-Q2_K

LM Studio

Download the GGUF file and load in LM Studio. Enable RotorQuant KV cache in advanced settings.

Specifications

Property	Value
Base Model	google/gemma-4-E4B
Parameters	~4B dense
Weight Quantization	GGUF Q2_K
KV Cache	RotorQuant 3-bit (planar/iso)
File Size	~2 GB
License	Apache 2.0
Compatible	llama.cpp, Ollama, LM Studio, koboldcpp

What is RotorQuant?

RotorQuant applies block-diagonal rotations (Clifford algebra) for KV cache compression. When used with llama.cpp's --cache-type-k planar3 --cache-type-v iso3 flags:

Metric	RotorQuant	TurboQuant
Prefill Speed	3,822 tok/s	722 tok/s
Decode Speed	119 tok/s	93 tok/s
Perplexity	6.91	7.07

See Also

• RotorQuant GitHub
• Base model
• MLX variants