Arao AI
Back to search results

gemma-4-E4B-it · Q2_K

Start a discussion
2x AMD Strix HaloStrata v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q2_K) on 2x AMD Strix Halo with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

311.82 tok/s

Decode

Decode speed

1,554.79 tok/s

Prefill

Prefill speed

1.96 s

TTFT

Time to first token

6.72 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 · IQ3_S Decode 197.35 · Prefill 823.81 ·
  2. vLLM · Q5_K_M Decode 149.23 · Prefill 534.97 ·
  3. Strata · Q2_K (current)Decode 311.82 · Prefill 1554.79 ·

Core figures

Decode (avg)
311.82 tok/s
Prefill (avg)
1,554.79 tok/s
TTFT (avg)
1.96 s
VRAM (avg)
6.72 GB
MTP acceptance rate
0.51
TTFB
2.49 GB
Power draw
108 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q2_K
Framework
Strata
Version
v0.53
Context length
8192 tokens
Batch size
1024
GPU layers
8
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
2x AMD Strix Halo
Measured VRAM (avg)
6.72 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
N/A
Power draw
108 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

    v0.53 · Ubuntu 24.04 · CUDA N/A · 8192 ctx

    311.82 tok/s

    Decode

    1,554.79 tok/s

    Prefill

    1.96 s

    TTFT

    6.72 GB

    VRAM

    0.51

    MTP

    108 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=88 running model_id=67 at Q2_K