gemma-4-E4B-it · IQ3_S
This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_S) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
105.34 tok/s
Decode
Decode speed
354.91 tok/s
Prefill
Prefill speed
0.91 s
TTFT
Time to first token
13.19 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
12 days ago
Last verified
Performance
- llama.cpp · IQ3_S (current)Decode 105.34 · Prefill 354.91 ·
- Ollama · IQ2_M Decode 116.68 · Prefill 432.72 ·
Core figures
- Decode (avg)
- 105.34 tok/s
- Prefill (avg)
- 354.91 tok/s
- TTFT (avg)
- 0.91 s
- VRAM (avg)
- 13.19 GB
- MTP acceptance rate
- —
- TTFB
- 0.84 GB
- Power draw
- 76.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- IQ3_S
- Framework
- llama.cpp
- Version
- v0.52
- Context length
- 65536 tokens
- Batch size
- 512
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 13.19 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 76.6 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Sources & evidence
1 measured records in total, each traceable to its original source
v0.52 · Ubuntu 24.04 · CUDA 13.0 · 65536 ctx
105.34 tok/s
Decode
354.91 tok/s
Prefill
0.91 s
TTFT
13.19 GB
VRAM
—
MTP
76.6 W
Power draw
L2 batch seed 2026-10-24: llama.cpp on hw_id=110 running model_id=67 at IQ3_S