Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q2_K

Start a discussion
NVIDIA RTX 508016GBStrata v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q2_K) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

333.42 tok/s

Decode

Decode speed

1,714.09 tok/s

Prefill

Prefill speed

1.12 s

TTFT

Time to first token

6.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

11 days ago

Last verified

Performance

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

Core figures

Decode (avg)
333.42 tok/s
Prefill (avg)
1,714.09 tok/s
TTFT (avg)
1.12 s
VRAM (avg)
6.72 GB
MTP acceptance rate
0.51
TTFB
2.67 GB
Power draw
267.8 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q2_K
Framework
Strata
Version
v0.47
Context length
4096 tokens
Batch size
256
GPU layers
8
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)
6.72 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.4
Power draw
267.8 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

    v0.47 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx

    333.42 tok/s

    Decode

    1,714.09 tok/s

    Prefill

    1.12 s

    TTFT

    6.72 GB

    VRAM

    0.51

    MTP

    267.8 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=14 running model_id=75 at Q2_K