Arao AI
Back to search results

Kimi-K3 · Q8_0

Start a discussion
NVIDIA RTX 508016GBOllama v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (Q8_0) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

85.12 tok/s

Decode

Decode speed

372.82 tok/s

Prefill

Prefill speed

0.69 s

TTFT

Time to first token

1.05 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 Decode 124.24 · Prefill 658.04 ·
  2. Ollama · Q8_0 (current)Decode 85.12 · Prefill 372.82 ·
  3. Strata · Q8_0 Decode 128.67 · Prefill 423.79 ·

Core figures

Decode (avg)
85.12 tok/s
Prefill (avg)
372.82 tok/s
TTFT (avg)
0.69 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.68 GB
Power draw
203.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
Q8_0
Framework
Ollama
Version
v0.23
Context length
4096 tokens
Batch size
512
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)
1.05 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.4
Power draw
203.3 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

    v0.23 · Windows 11 24H2 · CUDA 12.4 · 4096 ctx

    85.12 tok/s

    Decode

    372.82 tok/s

    Prefill

    0.69 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    203.3 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=14 running model_id=73 at Q8_0