Arao AI
Back to search results

gemma-4-E2B-it · FP16

Start a discussion
AMD Strix Point (Radeon 890M)Ollama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (FP16) on AMD Strix Point (Radeon 890M) with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

47.28 tok/s

Decode

Decode speed

250.08 tok/s

Prefill

Prefill speed

2.01 s

TTFT

Time to first token

9.87 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 · IQ1_S Decode 145.7 · Prefill 692.08 ·
  2. llama.cpp · IQ4_XS Decode 106.04 · Prefill 563.55 ·
  3. Ollama · FP16 (current)Decode 47.28 · Prefill 250.08 ·
  4. Ollama · Q8_0 Decode 57.25 · Prefill 264.02 ·

Core figures

Decode (avg)
47.28 tok/s
Prefill (avg)
250.08 tok/s
TTFT (avg)
2.01 s
VRAM (avg)
9.87 GB
MTP acceptance rate
—
TTFB
0.38 GB
Power draw
101.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
FP16
Framework
Ollama
Version
v0.48
Context length
16384 tokens
Batch size
512
GPU layers
28
Flash Attention
Off

Hardware

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

GPU
AMD Strix Point (Radeon 890M)
Measured VRAM (avg)
9.87 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
N/A
Power draw
101.2 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 · 16384 ctx

    47.28 tok/s

    Decode

    250.08 tok/s

    Prefill

    2.01 s

    TTFT

    9.87 GB

    VRAM

    —

    MTP

    101.2 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=89 running model_id=66 at FP16