Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q5_K_S

Start a discussion
NVIDIA H2097GBllama.cpp v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q5_K_S) on NVIDIA H20 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

116.43 tok/s

Decode

Decode speed

457.51 tok/s

Prefill

Prefill speed

0.72 s

TTFT

Time to first token

9.66 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 · Q5_K_S (current)Decode 116.43 · Prefill 457.51 ·
  2. Strata · IQ2_XS Decode 273.22 · Prefill 1069.33 ·

Core figures

Decode (avg)
116.43 tok/s
Prefill (avg)
457.51 tok/s
TTFT (avg)
0.72 s
VRAM (avg)
9.66 GB
MTP acceptance rate
—
TTFB
0.93 GB
Power draw
322.8 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.29
Context length
16384 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA H20
Nominal VRAM
97 GB
Measured VRAM (avg)
9.66 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.8
Power draw
322.8 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

    v0.29 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx

    116.43 tok/s

    Decode

    457.51 tok/s

    Prefill

    0.72 s

    TTFT

    9.66 GB

    VRAM

    —

    MTP

    322.8 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=56 running model_id=75 at Q5_K_S