Arao AI
Back to search results

gemma-4-E4B-it · Q8_0

Start a discussion
AMD Strix Halo (Radeon 8060S)Strata v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q8_0) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

92.35 tok/s

Decode

Decode speed

312.7 tok/s

Prefill

Prefill speed

1.41 s

TTFT

Time to first token

11.76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 142.24 · Prefill 506.53 ·
  2. Strata · Q8_0 (current)Decode 92.35 · Prefill 312.7 ·

Core figures

Decode (avg)
92.35 tok/s
Prefill (avg)
312.7 tok/s
TTFT (avg)
1.41 s
VRAM (avg)
11.76 GB
MTP acceptance rate
0.47
TTFB
0.74 GB
Power draw
102.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q8_0
Framework
Strata
Version
v0.25
Context length
16384 tokens
Batch size
256
GPU layers
15
Flash Attention
Off

Hardware

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

GPU
AMD Strix Halo (Radeon 8060S)
Measured VRAM (avg)
11.76 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
N/A
Power draw
102.1 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

    v0.25 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    92.35 tok/s

    Decode

    312.7 tok/s

    Prefill

    1.41 s

    TTFT

    11.76 GB

    VRAM

    0.47

    MTP

    102.1 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=67 at Q8_0