Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · Q3_K_S

Start a discussion
NVIDIA RTX 309024GBStrata v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q3_K_S) on NVIDIA RTX 3090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

133.25 tok/s

Decode

Decode speed

628.12 tok/s

Prefill

Prefill speed

1.73 s

TTFT

Time to first token

13.02 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

11 days ago

Last verified

Performance

  1. vLLM · Q4_K_S Decode 94.16 · Prefill 413.12 ·
  2. Strata · Q3_K_S (current)Decode 133.25 · Prefill 628.12 ·

Core figures

Decode (avg)
133.25 tok/s
Prefill (avg)
628.12 tok/s
TTFT (avg)
1.73 s
VRAM (avg)
13.02 GB
MTP acceptance rate
0.49
TTFB
1.07 GB
Power draw
319 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
Q3_K_S
Framework
Strata
Version
v0.30
Context length
8192 tokens
Batch size
256
GPU layers
8
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
13.02 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
12.8
Power draw
319 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

    v0.30 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    133.25 tok/s

    Decode

    628.12 tok/s

    Prefill

    1.73 s

    TTFT

    13.02 GB

    VRAM

    0.49

    MTP

    319 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=2 running model_id=74 at Q3_K_S