Arao AI
Back to search results

gemma-4-E4B-it · Q4_K_S

Start a discussion
Intel Arc A770 16GB16GBllama.cpp v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q4_K_S) on Intel Arc A770 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

63.45 tok/s

Decode

Decode speed

318.27 tok/s

Prefill

Prefill speed

1.25 s

TTFT

Time to first token

8.65 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 · Q3_K_M Decode 76.26 · Prefill 388.45 ·
  2. llama.cpp · Q4_K_S (current)Decode 63.45 · Prefill 318.27 ·
  3. Strata · Q3_K_L Decode 103.12 · Prefill 533.63 ·
  4. Strata · Q4_K_S Decode 90.28 · Prefill 352.31 ·

Core figures

Decode (avg)
63.45 tok/s
Prefill (avg)
318.27 tok/s
TTFT (avg)
1.25 s
VRAM (avg)
8.65 GB
MTP acceptance rate
—
TTFB
0.51 GB
Power draw
224.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.34
Context length
2048 tokens
Batch size
512
GPU layers
33
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)
8.65 GB
OS
Windows 11 23H2
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
224.5 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

    v0.34 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    63.45 tok/s

    Decode

    318.27 tok/s

    Prefill

    1.25 s

    TTFT

    8.65 GB

    VRAM

    —

    MTP

    224.5 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=97 running model_id=67 at Q4_K_S