Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · Q5_K_M

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q5_K_M) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

70.36 tok/s

Decode

Decode speed

357.32 tok/s

Prefill

Prefill speed

2.33 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

12 days ago

Last verified

Performance

  1. vLLM · Q5_K_M (current)Decode 70.36 · Prefill 357.32 ·
  2. Ollama · IQ3_S Decode 86.72 · Prefill 439.93 ·

Core figures

Decode (avg)
70.36 tok/s
Prefill (avg)
357.32 tok/s
TTFT (avg)
2.33 s
VRAM (avg)
17.72 GB
MTP acceptance rate
—
TTFB
0.56 GB
Power draw
267.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
Q5_K_M
Framework
vLLM
Version
v0.48
Context length
4096 tokens
Batch size
16
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
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
17.72 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
12.4
Power draw
267.5 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

    v0.48 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx

    70.36 tok/s

    Decode

    357.32 tok/s

    Prefill

    2.33 s

    TTFT

    17.72 GB

    VRAM

    —

    MTP

    267.5 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=11 running model_id=74 at Q5_K_M