Arao AI
Back to search results

Llama-3-8B-Instruct · Q2_K

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q2_K) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

349.23 tok/s

Decode

Decode speed

1,726.15 tok/s

Prefill

Prefill speed

1.71 s

TTFT

Time to first token

11.34 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 289.19 · Prefill 992.46 ·
  2. llama.cpp · IQ4_XS Decode 283.18 · Prefill 981.02 ·
  3. vLLM · Q2_K (current)Decode 349.23 · Prefill 1726.15 ·

Core figures

Decode (avg)
349.23 tok/s
Prefill (avg)
1,726.15 tok/s
TTFT (avg)
1.71 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
2.79 GB
Power draw
659.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q2_K
Framework
vLLM
Version
v0.37
Context length
32768 tokens
Batch size
32
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
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
11.34 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.8
Power draw
659.5 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

    v0.37 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    349.23 tok/s

    Decode

    1,726.15 tok/s

    Prefill

    1.71 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    659.5 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=69 at Q2_K