Back to search results
gemma-4-E4B-it · IQ4_XS
NVIDIA RTX 309024GBvLLM v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ4_XS) on NVIDIA RTX 3090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
102.62 tok/s
Decode
Decode speed
342.57 tok/s
Prefill
Prefill speed
1.22 s
TTFT
Time to first token
14.53 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
11 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 121.92 · Prefill 447.63 ·
- vLLM · IQ4_XS (current)Decode 102.62 · Prefill 342.57 ·
Core figures
- Decode (avg)
- 102.62 tok/s
- Prefill (avg)
- 342.57 tok/s
- TTFT (avg)
- 1.22 s
- VRAM (avg)
- 14.53 GB
- MTP acceptance rate
- —
- TTFB
- 0.82 GB
- Power draw
- 336.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.54
- Context length
- 8192 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 14.53 GB
- OS
- Windows 11 24H2
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 336.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Windows 11 24H2 · CUDA 12.8 · 8192 ctx
102.62 tok/s
Decode
342.57 tok/s
Prefill
1.22 s
TTFT
14.53 GB
VRAM
—
MTP
336.1 W
Power draw
L2 batch seed 2026-10-24: vLLM on hw_id=2 running model_id=67 at IQ4_XS