Arao AI
Back to search results

iFlytek Spark-X2.5-4B · IQ2_M

Start a discussion
Apple M5 Ultra512GBllama.cpp v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ2_M) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

381.7 tok/s

Decode

Decode speed

1,687.3 tok/s

Prefill

Prefill speed

2.48 s

TTFT

Time to first token

6.47 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 · IQ2_M (current)Decode 381.7 · Prefill 1687.3 ·
  2. Ollama · IQ2_XS Decode 337.8 · Prefill 1438.9 ·

Core figures

Decode (avg)
381.7 tok/s
Prefill (avg)
1,687.3 tok/s
TTFT (avg)
2.48 s
VRAM (avg)
6.47 GB
MTP acceptance rate
—
TTFB
3.05 GB
Power draw
108.6 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.34
Context length
16384 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 M5 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
6.47 GB
OS
macOS 26.1
Power draw
108.6 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

    v0.34 · macOS 26.1 · 16384 ctx

    381.7 tok/s

    Decode

    1,687.3 tok/s

    Prefill

    2.48 s

    TTFT

    6.47 GB

    VRAM

    —

    MTP

    108.6 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=29 running model_id=75 at IQ2_M