Arao AI
Back to search results

gemma-4-E2B-it · Q6_K

Start a discussion
AMD Strix Halo (Radeon 8060S)Strata v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q6_K) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

157.75 tok/s

Decode

Decode speed

603.58 tok/s

Prefill

Prefill speed

1.61 s

TTFT

Time to first token

6.3 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · FP16 Decode 70.57 · Prefill 330.84 ·
  2. Strata · Q3_K_S Decode 228.54 · Prefill 966.84 ·
  3. Strata · Q6_K (current)Decode 157.75 · Prefill 603.58 ·

Core figures

Decode (avg)
157.75 tok/s
Prefill (avg)
603.58 tok/s
TTFT (avg)
1.61 s
VRAM (avg)
6.3 GB
MTP acceptance rate
0.58
TTFB
1.26 GB
Power draw
86.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q6_K
Framework
Strata
Version
v0.48
Context length
2048 tokens
Batch size
512
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)
6.3 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
86.4 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

    v0.48 · Windows 11 23H2 · CUDA N/A · 2048 ctx

    157.75 tok/s

    Decode

    603.58 tok/s

    Prefill

    1.61 s

    TTFT

    6.3 GB

    VRAM

    0.58

    MTP

    86.4 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=66 at Q6_K