Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q3_K_L

Start a discussion
AMD Radeon RX 7900 XTX24GBOllama v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q3_K_L) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

216.92 tok/s

Decode

Decode speed

1,042.56 tok/s

Prefill

Prefill speed

0.49 s

TTFT

Time to first token

8.15 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. vLLM · Q5_K_S Decode 190.47 · Prefill 971.18 ·
  2. Ollama · Q3_K_L (current)Decode 216.92 · Prefill 1042.56 ·

Core figures

Decode (avg)
216.92 tok/s
Prefill (avg)
1,042.56 tok/s
TTFT (avg)
0.49 s
VRAM (avg)
8.15 GB
MTP acceptance rate
—
TTFB
1.74 GB
Power draw
200.3 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q3_K_L
Framework
Ollama
Version
v0.44
Context length
8192 tokens
Batch size
512
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
8.15 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
12.4
Power draw
200.3 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

    v0.44 · Windows 11 23H2 · CUDA 12.4 · 8192 ctx

    216.92 tok/s

    Decode

    1,042.56 tok/s

    Prefill

    0.49 s

    TTFT

    8.15 GB

    VRAM

    —

    MTP

    200.3 W

    Power draw

    L2 batch seed 2026-10-24: Ollama on hw_id=11 running model_id=75 at Q3_K_L