Arao AI
Back to search results

Qwen3-8B · Q5_K_S

Start a discussion
NVIDIA RTX 508016GBllama.cpp v0.48L2 Cross-framework verified

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

91.75 tok/s

Decode

Decode speed

454.66 tok/s

Prefill

Prefill speed

0.91 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. llama.cpp · Q5_K_S (current)Decode 91.75 · Prefill 454.66 ·
  2. Ollama · Q3_K_L Decode 101.88 · Prefill 405.42 ·
  3. Strata · IQ4_XS Decode 144.31 · Prefill 545.08 ·

Core figures

Decode (avg)
91.75 tok/s
Prefill (avg)
454.66 tok/s
TTFT (avg)
0.91 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.73 GB
Power draw
261.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.48
Context length
8192 tokens
Batch size
256
GPU layers
28
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
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
261.2 W

Sources & evidence

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

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

    v0.48 · Ubuntu 22.04 · CUDA 12.6 · 8192 ctx

    91.75 tok/s

    Decode

    454.66 tok/s

    Prefill

    0.91 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    261.2 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=14 running model_id=53 at Q5_K_S