Arao AI
Back to search results

iFlytek Spark-X2.5-4B · Q3_K_L

Start a discussion
Intel Arc B58012GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q3_K_L) on Intel Arc B580 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

127.75 tok/s

Decode

Decode speed

669.2 tok/s

Prefill

Prefill speed

1.02 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

11 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 164.15 · Prefill 679.38 ·
  2. Ollama · Q3_K_L (current)Decode 127.75 · Prefill 669.2 ·

Core figures

Decode (avg)
127.75 tok/s
Prefill (avg)
669.2 tok/s
TTFT (avg)
1.02 s
VRAM (avg)
8.15 GB
MTP acceptance rate
—
TTFB
1.02 GB
Power draw
151.9 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
v0.34
Context length
4096 tokens
Batch size
256
GPU layers
28
Flash Attention
Off

Hardware

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

GPU
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
8.15 GB
OS
Ubuntu 24.04
Driver
Intel Arc 32.0.101.6552
CUDA
12.6
Power draw
151.9 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 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    127.75 tok/s

    Decode

    669.2 tok/s

    Prefill

    1.02 s

    TTFT

    8.15 GB

    VRAM

    —

    MTP

    151.9 W

    Power draw

    L2 batch seed 2026-10-24: Ollama on hw_id=94 running model_id=75 at Q3_K_L