Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · IQ3_S

Start a discussion
AMD Radeon RX 7900 XTX24GBOllama v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (IQ3_S) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

86.72 tok/s

Decode

Decode speed

439.93 tok/s

Prefill

Prefill speed

1.71 s

TTFT

Time to first token

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

Core figures

Decode (avg)
86.72 tok/s
Prefill (avg)
439.93 tok/s
TTFT (avg)
1.71 s
VRAM (avg)
13.19 GB
MTP acceptance rate
—
TTFB
0.69 GB
Power draw
220.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
IQ3_S
Framework
Ollama
Version
v0.31
Context length
16384 tokens
Batch size
512
GPU layers
99
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)
13.19 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.4
Power draw
220.2 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

    v0.31 · Ubuntu 24.04 · CUDA 12.4 · 16384 ctx

    86.72 tok/s

    Decode

    439.93 tok/s

    Prefill

    1.71 s

    TTFT

    13.19 GB

    VRAM

    —

    MTP

    220.2 W

    Power draw

    L2 batch seed 2026-10-24: Ollama on hw_id=11 running model_id=74 at IQ3_S