Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q5_K_S

Start a discussion
NVIDIA RTX 508016GBOllama v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q5_K_S) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

149.47 tok/s

Decode

Decode speed

563.58 tok/s

Prefill

Prefill speed

1.49 s

TTFT

Time to first token

15.2 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 · Q5_K_S (current)Decode 149.47 · Prefill 563.58 ·
  2. Strata · IQ3_S Decode 302.96 · Prefill 1550.76 ·
  3. vLLM · IQ4_XS Decode 224.27 · Prefill 989.89 ·
  4. Strata · IQ3_XS Decode 308.04 · Prefill 1362.37 ·
  5. Strata · Q3_K_S Decode 323.81 · Prefill 1737.95 ·

Core figures

Decode (avg)
149.47 tok/s
Prefill (avg)
563.58 tok/s
TTFT (avg)
1.49 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1.2 GB
Power draw
322.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q5_K_S
Framework
Ollama
Version
v0.21
Context length
4096 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 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.4
Power draw
322.4 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

    v0.21 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx

    149.47 tok/s

    Decode

    563.58 tok/s

    Prefill

    1.49 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    322.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=14 running model_id=68 at Q5_K_S