Back to search results
gemma-4-E4B-it · IQ2_XS
NVIDIA RTX 508016GBvLLM v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ2_XS) on NVIDIA RTX 5080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
301.33 tok/s
Decode
Decode speed
1,596.94 tok/s
Prefill
Prefill speed
1.8 s
TTFT
Time to first token
10.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
11 days ago
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 301.33 · Prefill 1596.94 ·
- Strata · IQ4_XS Decode 314.5 · Prefill 1280.69 ·
Core figures
- Decode (avg)
- 301.33 tok/s
- Prefill (avg)
- 1,596.94 tok/s
- TTFT (avg)
- 1.8 s
- VRAM (avg)
- 10.16 GB
- MTP acceptance rate
- —
- TTFB
- 2.41 GB
- Power draw
- 283.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.37
- Context length
- 8192 tokens
- Batch size
- 32
- 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 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 10.16 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 283.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx
301.33 tok/s
Decode
1,596.94 tok/s
Prefill
1.8 s
TTFT
10.16 GB
VRAM
—
MTP
283.4 W
Power draw
L2 batch seed 2026-10-24: vLLM on hw_id=14 running model_id=67 at IQ2_XS