Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · IQ3_XS

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (IQ3_XS) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

72.77 tok/s

Decode

Decode speed

239.26 tok/s

Prefill

Prefill speed

2.3 s

TTFT

Time to first token

12.52 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 · IQ3_XS (current)Decode 72.77 · Prefill 239.26 ·
  2. Ollama · IQ3_XS Decode 66.41 · Prefill 229.61 ·

Core figures

Decode (avg)
72.77 tok/s
Prefill (avg)
239.26 tok/s
TTFT (avg)
2.3 s
VRAM (avg)
12.52 GB
MTP acceptance rate
—
TTFB
0.58 GB
Power draw
63.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
IQ3_XS
Framework
llama.cpp
Version
v0.40
Context length
8192 tokens
Batch size
256
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
NVIDIA RTX Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
12.52 GB
OS
Ubuntu 24.04
Driver
615.78
CUDA
13.0
Power draw
63.9 W
Reference price
$2,399 · updated 2026-10-19

Prices are not live; check the store page

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-24

    v0.40 · Ubuntu 24.04 · CUDA 13.0 · 8192 ctx

    72.77 tok/s

    Decode

    239.26 tok/s

    Prefill

    2.3 s

    TTFT

    12.52 GB

    VRAM

    —

    MTP

    63.9 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=110 running model_id=74 at IQ3_XS