Back to search results
gemma-4-E2B-it · IQ3_S
NVIDIA RTX 509032GBStrata v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ3_S) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
332.29 tok/s
Decode
Decode speed
1,223.54 tok/s
Prefill
Prefill speed
2.29 s
TTFT
Time to first token
4.87 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · Q3_K_L Decode 324.42 · Prefill 1387.31 ·
- Strata · IQ3_S (current)Decode 332.29 · Prefill 1223.54 ·
Core figures
- Decode (avg)
- 332.29 tok/s
- Prefill (avg)
- 1,223.54 tok/s
- TTFT (avg)
- 2.29 s
- VRAM (avg)
- 4.87 GB
- MTP acceptance rate
- 0.53
- TTFB
- 2.66 GB
- Power draw
- 465.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- IQ3_S
- Framework
- Strata
- Version
- v0.40
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 12
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 4.87 GB
- OS
- macOS 15.0
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 465.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · macOS 15.0 · CUDA 12.4 · 16384 ctx
332.29 tok/s
Decode
1,223.54 tok/s
Prefill
2.29 s
TTFT
4.87 GB
VRAM
0.53
MTP
465.1 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=13 running model_id=66 at IQ3_S