Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q5_K_M

Start a discussion
NVIDIA H2097GBOllama v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q5_K_M) on NVIDIA H20 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

43.67 tok/s

Decode

Decode speed

144.84 tok/s

Prefill

Prefill speed

1.35 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

17 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 65.35 · Prefill 226.54 ·
  2. Ollama · IQ3_S Decode 56.57 · Prefill 208.48 ·
  3. Ollama · Q5_K_M (current)Decode 43.67 · Prefill 144.84 ·

Core figures

Decode (avg)
43.67 tok/s
Prefill (avg)
144.84 tok/s
TTFT (avg)
1.35 s
VRAM (avg)
17.72 GB
MTP acceptance rate
—
TTFB
0.35 GB
Power draw
377.4 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
v0.23
Context length
2048 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
NVIDIA H20
Nominal VRAM
97 GB
Measured VRAM (avg)
17.72 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
377.4 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

    v0.23 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx

    43.67 tok/s

    Decode

    144.84 tok/s

    Prefill

    1.35 s

    TTFT

    17.72 GB

    VRAM

    —

    MTP

    377.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=56 running model_id=68 at Q5_K_M