Arao AI
Back to search results

gemma-4-E4B-it · Q3_K_S

Start a discussion
NVIDIA RTX 509032GBStrata v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q3_K_S) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

326.07 tok/s

Decode

Decode speed

1,598 tok/s

Prefill

Prefill speed

0.35 s

TTFT

Time to first token

7.56 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · Q3_K_L Decode 336.48 · Prefill 1309.15 ·
  2. vLLM · Q3_K_S Decode 310.95 · Prefill 1691.37 ·
  3. Strata · Q3_K_S (current)Decode 326.07 · Prefill 1598 ·
  4. Strata · Q5_K_M Decode 361.26 · Prefill 1894.18 ·

Core figures

Decode (avg)
326.07 tok/s
Prefill (avg)
1,598 tok/s
TTFT (avg)
0.35 s
VRAM (avg)
7.56 GB
MTP acceptance rate
0.68
TTFB
2.61 GB
Power draw
294.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q3_K_S
Framework
Strata
Version
v0.30
Context length
2048 tokens
Batch size
256
GPU layers
5
Flash Attention
Off

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)
7.56 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.8
Power draw
294.2 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.30 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx

    326.07 tok/s

    Decode

    1,598 tok/s

    Prefill

    0.35 s

    TTFT

    7.56 GB

    VRAM

    0.68

    MTP

    294.2 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=13 running model_id=67 at Q3_K_S