Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q5_K_M

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q5_K_M) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

184.14 tok/s

Decode

Decode speed

644.68 tok/s

Prefill

Prefill speed

1.37 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

16 days ago

Last verified

Performance

  1. Ollama · Q3_K_L Decode 262.13 · Prefill 1148.25 ·
  2. Ollama · Q5_K_M (current)Decode 184.14 · Prefill 644.68 ·
  3. Strata · IQ4_XS Decode 387.3 · Prefill 1749.15 ·

Core figures

Decode (avg)
184.14 tok/s
Prefill (avg)
644.68 tok/s
TTFT (avg)
1.37 s
VRAM (avg)
17.72 GB
MTP acceptance rate
—
TTFB
1.47 GB
Power draw
390.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q5_K_M
Framework
Ollama
Version
v0.26
Context length
32768 tokens
Batch size
256
GPU layers
28
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
Ubuntu 24.04
Driver
570.86
CUDA
12.4
Power draw
390.5 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.26 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    184.14 tok/s

    Decode

    644.68 tok/s

    Prefill

    1.37 s

    TTFT

    17.72 GB

    VRAM

    —

    MTP

    390.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=68 at Q5_K_M