Arao AI
Back to search results

Qwen3-8B · Q5_K_S

Start a discussion
NVIDIA RTX 508016GBOllama v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_S) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

128.2 tok/s

Decode

Decode speed

585.03 tok/s

Prefill

Prefill speed

0.31 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

Today

Last verified

Performance

  1. Ollama · Q5_K_S (current)Decode 128.2 · Prefill 585.03 ·
  2. Strata · IQ1_S Decode 376.58 · Prefill 1681.2 ·
  3. llama.cpp · Q5_K_S Decode 91.75 · Prefill 454.66 ·
  4. Ollama · Q3_K_L Decode 101.88 · Prefill 405.42 ·
  5. Strata · IQ4_XS Decode 144.31 · Prefill 545.08 ·

Core figures

Decode (avg)
128.2 tok/s
Prefill (avg)
585.03 tok/s
TTFT (avg)
0.31 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1.03 GB
Power draw
277.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q5_K_S
Framework
Ollama
Version
v0.50
Context length
4096 tokens
Batch size
512
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 RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
13.0
Power draw
277.7 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.50 · Windows 11 24H2 · CUDA 13.0 · 4096 ctx

    128.2 tok/s

    Decode

    585.03 tok/s

    Prefill

    0.31 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    277.7 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=14 running model_id=53 at Q5_K_S