Arao AI
Back to search results

gemma-4-E4B-it · Q4_K_M

Start a discussion
Intel Arc 140VOllama v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q4_K_M) on Intel Arc 140V with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

56.25 tok/s

Decode

Decode speed

293.11 tok/s

Prefill

Prefill speed

2.06 s

TTFT

Time to first token

8.99 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 · Q4_K_M (current)Decode 56.25 · Prefill 293.11 ·
  2. Strata · Q8_0 Decode 61.68 · Prefill 298.98 ·

Core figures

Decode (avg)
56.25 tok/s
Prefill (avg)
293.11 tok/s
TTFT (avg)
2.06 s
VRAM (avg)
8.99 GB
MTP acceptance rate
—
TTFB
0.45 GB
Power draw
157 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q4_K_M
Framework
Ollama
Version
v0.22
Context length
32768 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
Intel Arc 140V
Measured VRAM (avg)
8.99 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
157 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

    v0.22 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx

    56.25 tok/s

    Decode

    293.11 tok/s

    Prefill

    2.06 s

    TTFT

    8.99 GB

    VRAM

    —

    MTP

    157 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=98 running model_id=67 at Q4_K_M