Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q4_K_M

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q4_K_M) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

82.35 tok/s

Decode

Decode speed

342.05 tok/s

Prefill

Prefill speed

0.56 s

TTFT

Time to first token

8.99 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

11 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M (current)Decode 82.35 · Prefill 342.05 ·
  2. Ollama · IQ3_S Decode 107.47 · Prefill 568.49 ·

Core figures

Decode (avg)
82.35 tok/s
Prefill (avg)
342.05 tok/s
TTFT (avg)
0.56 s
VRAM (avg)
8.99 GB
MTP acceptance rate
—
TTFB
0.66 GB
Power draw
51.2 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.45
Context length
65536 tokens
Batch size
256
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 RTX Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
8.99 GB
OS
Ubuntu 24.04
Driver
615.78
CUDA
13.0
Power draw
51.2 W
Reference price
$2,399 · updated 2026-10-19

Prices are not live; check the store page

Sources & evidence

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

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

    v0.45 · Ubuntu 24.04 · CUDA 13.0 · 65536 ctx

    82.35 tok/s

    Decode

    342.05 tok/s

    Prefill

    0.56 s

    TTFT

    8.99 GB

    VRAM

    —

    MTP

    51.2 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=110 running model_id=75 at Q4_K_M