Arao AI
Back to search results

iFlytek Spark-X2.5-4B · IQ1_S

Start a discussion
NVIDIA RTX 508016GBvLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ1_S) on NVIDIA RTX 5080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

296.57 tok/s

Decode

Decode speed

1,519.02 tok/s

Prefill

Prefill speed

2.29 s

TTFT

Time to first token

5.63 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. vLLM · IQ1_S (current)Decode 296.57 · Prefill 1519.02 ·
  2. Strata · Q2_K Decode 333.42 · Prefill 1714.09 ·

Core figures

Decode (avg)
296.57 tok/s
Prefill (avg)
1,519.02 tok/s
TTFT (avg)
2.29 s
VRAM (avg)
5.63 GB
MTP acceptance rate
—
TTFB
2.37 GB
Power draw
299 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
IQ1_S
Framework
vLLM
Version
v0.30
Context length
32768 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
5.63 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.8
Power draw
299 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

    v0.30 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx

    296.57 tok/s

    Decode

    1,519.02 tok/s

    Prefill

    2.29 s

    TTFT

    5.63 GB

    VRAM

    —

    MTP

    299 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=14 running model_id=75 at IQ1_S