Arao AI
Back to search results

iFlytek Spark-X2.5-4B · IQ4_XS

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ4_XS) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

84.12 tok/s

Decode

Decode speed

383.03 tok/s

Prefill

Prefill speed

1.57 s

TTFT

Time to first token

8.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 115.1 · Prefill 632.07 ·
  2. vLLM · IQ4_XS (current)Decode 84.12 · Prefill 383.03 ·

Core figures

Decode (avg)
84.12 tok/s
Prefill (avg)
383.03 tok/s
TTFT (avg)
1.57 s
VRAM (avg)
8.32 GB
MTP acceptance rate
—
TTFB
0.67 GB
Power draw
68.1 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
IQ4_XS
Framework
vLLM
Version
v0.37
Context length
8192 tokens
Batch size
8
GPU layers
999
Flash Attention
On

Hardware

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

GPU
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
8.32 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.8
Power draw
68.1 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-24

    v0.37 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    84.12 tok/s

    Decode

    383.03 tok/s

    Prefill

    1.57 s

    TTFT

    8.32 GB

    VRAM

    —

    MTP

    68.1 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=24 running model_id=75 at IQ4_XS