Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · Q5_K_M

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBStrata v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q5_K_M) on NVIDIA RTX PRO 6000 Blackwell 96GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

252.2 tok/s

Decode

Decode speed

1,116.29 tok/s

Prefill

Prefill speed

0.51 s

TTFT

Time to first token

17.72 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 · Q2_K Decode 326.52 · Prefill 1378.65 ·
  2. Strata · Q5_K_M (current)Decode 252.2 · Prefill 1116.29 ·

Core figures

Decode (avg)
252.2 tok/s
Prefill (avg)
1,116.29 tok/s
TTFT (avg)
0.51 s
VRAM (avg)
17.72 GB
MTP acceptance rate
0.71
TTFB
2.02 GB
Power draw
388.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
Q5_K_M
Framework
Strata
Version
v0.21
Context length
4096 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 PRO 6000 Blackwell 96GB
Nominal VRAM
96 GB
Measured VRAM (avg)
17.72 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.4
Power draw
388.6 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

    v0.21 · Windows 11 23H2 · CUDA 12.4 · 4096 ctx

    252.2 tok/s

    Decode

    1,116.29 tok/s

    Prefill

    0.51 s

    TTFT

    17.72 GB

    VRAM

    0.71

    MTP

    388.6 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=68 running model_id=74 at Q5_K_M