Arao AI
Back to search results

Qwen3-8B · Q4_K_S

Start a discussion
NVIDIA RTX 5070 Ti16GBOllama v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q4_K_S) on NVIDIA RTX 5070 Ti with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

82.54 tok/s

Decode

Decode speed

372.44 tok/s

Prefill

Prefill speed

1.82 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 · Q3_K_M Decode 110.54 · Prefill 601.05 ·
  2. Ollama · Q4_K_S (current)Decode 82.54 · Prefill 372.44 ·

Core figures

Decode (avg)
82.54 tok/s
Prefill (avg)
372.44 tok/s
TTFT (avg)
1.82 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.66 GB
Power draw
243.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q4_K_S
Framework
Ollama
Version
v0.53
Context length
16384 tokens
Batch size
512
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 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
13.0
Power draw
243.9 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

    v0.53 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx

    82.54 tok/s

    Decode

    372.44 tok/s

    Prefill

    1.82 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    243.9 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=17 running model_id=53 at Q4_K_S