Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q3_K_S

Start a discussion
NVIDIA H100 80GB HBM380GBStrata v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q3_K_S) on NVIDIA H100 80GB HBM3 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

291.71 tok/s

Decode

Decode speed

1,407.26 tok/s

Prefill

Prefill speed

1.33 s

TTFT

Time to first token

7.56 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. Ollama · IQ2_XS Decode 285.58 · Prefill 1151.82 ·
  2. Strata · Q3_K_S (current)Decode 291.71 · Prefill 1407.26 ·

Core figures

Decode (avg)
291.71 tok/s
Prefill (avg)
1,407.26 tok/s
TTFT (avg)
1.33 s
VRAM (avg)
7.56 GB
MTP acceptance rate
0.69
TTFB
2.33 GB
Power draw
683.2 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q3_K_S
Framework
Strata
Version
v0.53
Context length
65536 tokens
Batch size
256
GPU layers
5
Flash Attention
Off

Hardware

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

GPU
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
7.56 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
13.0
Power draw
683.2 W

Sources & evidence

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

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

    v0.53 · Ubuntu 24.04 · CUDA 13.0 · 65536 ctx

    291.71 tok/s

    Decode

    1,407.26 tok/s

    Prefill

    1.33 s

    TTFT

    7.56 GB

    VRAM

    0.69

    MTP

    683.2 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=55 running model_id=75 at Q3_K_S