Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q8_0

Start a discussion
NVIDIA RTX 4080 Super16GBllama.cpp v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q8_0) on NVIDIA RTX 4080 Super with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

237.08 tok/s

Decode

Decode speed

981.54 tok/s

Prefill

Prefill speed

0.71 s

TTFT

Time to first token

11.76 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 · Q8_0 (current)Decode 237.08 · Prefill 981.54 ·
  2. Strata · Q4_K_M Decode 305.26 · Prefill 1292.84 ·

Core figures

Decode (avg)
237.08 tok/s
Prefill (avg)
981.54 tok/s
TTFT (avg)
0.71 s
VRAM (avg)
11.76 GB
MTP acceptance rate
—
TTFB
1.9 GB
Power draw
235.3 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q8_0
Framework
llama.cpp
Version
v0.33
Context length
8192 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
11.76 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.6
Power draw
235.3 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

    v0.33 · Windows 11 24H2 · CUDA 12.6 · 8192 ctx

    237.08 tok/s

    Decode

    981.54 tok/s

    Prefill

    0.71 s

    TTFT

    11.76 GB

    VRAM

    —

    MTP

    235.3 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=20 running model_id=75 at Q8_0