Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q2_K

Start a discussion
Apple M2 Ultrallama.cpp v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q2_K) on Apple M2 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

325.56 tok/s

Decode

Decode speed

1,312.17 tok/s

Prefill

Prefill speed

0.63 s

TTFT

Time to first token

6.72 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 · Q2_K (current)Decode 325.56 · Prefill 1312.17 ·
  2. Ollama · IQ4_XS Decode 260.88 · Prefill 1133.93 ·

Core figures

Decode (avg)
325.56 tok/s
Prefill (avg)
1,312.17 tok/s
TTFT (avg)
0.63 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
2.6 GB
Power draw
129.2 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.44
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
Apple M2 Ultra
Measured VRAM (avg)
6.72 GB
OS
macOS 26.1
Power draw
129.2 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

    v0.44 · macOS 26.1 · 8192 ctx

    325.56 tok/s

    Decode

    1,312.17 tok/s

    Prefill

    0.63 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    129.2 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=103 running model_id=75 at Q2_K