Arao AI
Back to search results

iFlytek Spark-X2.5-4B · IQ2_M

Start a discussion
NVIDIA RTX 3060 12GB12GBOllama v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ2_M) on NVIDIA RTX 3060 12GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

182.69 tok/s

Decode

Decode speed

954.31 tok/s

Prefill

Prefill speed

2.47 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. Ollama · IQ2_M (current)Decode 182.69 · Prefill 954.31 ·
  2. Strata · Q4_K_S Decode 203.46 · Prefill 1004.82 ·

Core figures

Decode (avg)
182.69 tok/s
Prefill (avg)
954.31 tok/s
TTFT (avg)
2.47 s
VRAM (avg)
6.47 GB
MTP acceptance rate
—
TTFB
1.46 GB
Power draw
162.8 W

Configuration

Member-level fields are taken from the most recent run

Model
iFlytek Spark-X2.5-4B
Quantization
IQ2_M
Framework
Ollama
Version
v0.32
Context length
32768 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
6.47 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
162.8 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

    v0.32 · Windows 11 23H2 · CUDA 12.6 · 32768 ctx

    182.69 tok/s

    Decode

    954.31 tok/s

    Prefill

    2.47 s

    TTFT

    6.47 GB

    VRAM

    —

    MTP

    162.8 W

    Power draw

    L2 batch seed 2026-10-24: Ollama on hw_id=15 running model_id=75 at IQ2_M