Arao AI
Back to search results

gemma-4-E2B-it · Q4_K_M

Start a discussion
Intel Arc A770 16GB16GBStrata v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q4_K_M) on Intel Arc A770 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

120.11 tok/s

Decode

Decode speed

549.54 tok/s

Prefill

Prefill speed

2.31 s

TTFT

Time to first token

5.54 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 · Q6_K Decode 63.94 · Prefill 244.56 ·
  2. Strata · Q4_K_M (current)Decode 120.11 · Prefill 549.54 ·

Core figures

Decode (avg)
120.11 tok/s
Prefill (avg)
549.54 tok/s
TTFT (avg)
2.31 s
VRAM (avg)
5.54 GB
MTP acceptance rate
0.7
TTFB
0.96 GB
Power draw
205.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q4_K_M
Framework
Strata
Version
v0.27
Context length
16384 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
Intel Arc A770 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
5.54 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
205.8 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

    v0.27 · Ubuntu 24.04 · CUDA 12.6 · 16384 ctx

    120.11 tok/s

    Decode

    549.54 tok/s

    Prefill

    2.31 s

    TTFT

    5.54 GB

    VRAM

    0.7

    MTP

    205.8 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=97 running model_id=66 at Q4_K_M