Arao AI
Back to search results

Llama-3-8B-Instruct · Q6_K

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q6_K) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

185.73 tok/s

Decode

Decode speed

814.54 tok/s

Prefill

Prefill speed

0.75 s

TTFT

Time to first token

18.9 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 345.66 · Prefill 1718.2 ·
  2. llama.cpp · Q5_K_M Decode 194.41 · Prefill 877.5 ·
  3. Ollama · Q3_K_M Decode 249.19 · Prefill 1206.14 ·
  4. Ollama · Q6_K (current)Decode 185.73 · Prefill 814.54 ·

Core figures

Decode (avg)
185.73 tok/s
Prefill (avg)
814.54 tok/s
TTFT (avg)
0.75 s
VRAM (avg)
18.9 GB
MTP acceptance rate
—
TTFB
1.49 GB
Power draw
321.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q6_K
Framework
Ollama
Version
v0.30
Context length
8192 tokens
Batch size
512
GPU layers
20
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)
18.9 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.4
Power draw
321.9 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

    v0.30 · Ubuntu 22.04 · CUDA 12.4 · 8192 ctx

    185.73 tok/s

    Decode

    814.54 tok/s

    Prefill

    0.75 s

    TTFT

    18.9 GB

    VRAM

    —

    MTP

    321.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=69 at Q6_K