Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · Q3_K_M

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q3_K_M) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

321.73 tok/s

Decode

Decode speed

1,464.84 tok/s

Prefill

Prefill speed

1.23 s

TTFT

Time to first token

13.52 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 · Q8_0 Decode 271.67 · Prefill 1471.82 ·
  2. vLLM · Q3_K_M (current)Decode 321.73 · Prefill 1464.84 ·

Core figures

Decode (avg)
321.73 tok/s
Prefill (avg)
1,464.84 tok/s
TTFT (avg)
1.23 s
VRAM (avg)
13.52 GB
MTP acceptance rate
—
TTFB
2.57 GB
Power draw
675.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
Q3_K_M
Framework
vLLM
Version
v0.29
Context length
16384 tokens
Batch size
8
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
13.52 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.8
Power draw
675.7 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

    v0.29 · Ubuntu 22.04 · CUDA 12.8 · 16384 ctx

    321.73 tok/s

    Decode

    1,464.84 tok/s

    Prefill

    1.23 s

    TTFT

    13.52 GB

    VRAM

    —

    MTP

    675.7 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=55 running model_id=74 at Q3_K_M