Arao AI
Back to search results

Llama-3-8B-Instruct · Q8_0

Start a discussion
NVIDIA H2097GBOllama v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q8_0) on NVIDIA H20 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

36.49 tok/s

Decode

Decode speed

129.53 tok/s

Prefill

Prefill speed

2.25 s

TTFT

Time to first token

21.42 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · Q2_K Decode 77.65 · Prefill 286.25 ·
  2. Ollama · Q5_K_M Decode 41.54 · Prefill 137.1 ·
  3. Ollama · Q8_0 (current)Decode 36.49 · Prefill 129.53 ·

Core figures

Decode (avg)
36.49 tok/s
Prefill (avg)
129.53 tok/s
TTFT (avg)
2.25 s
VRAM (avg)
21.42 GB
MTP acceptance rate
—
TTFB
0.29 GB
Power draw
399 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q8_0
Framework
Ollama
Version
v0.40
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
NVIDIA H20
Nominal VRAM
97 GB
Measured VRAM (avg)
21.42 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
399 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

    v0.40 · Ubuntu 22.04 · CUDA 12.6 · 8192 ctx

    36.49 tok/s

    Decode

    129.53 tok/s

    Prefill

    2.25 s

    TTFT

    21.42 GB

    VRAM

    —

    MTP

    399 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=56 running model_id=69 at Q8_0