Arao AI
Back to search results

Kimi-K3 · Q5_K_S

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBvLLM v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (Q5_K_S) on NVIDIA RTX 4060 Ti 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

82.77 tok/s

Decode

Decode speed

438.83 tok/s

Prefill

Prefill speed

2.43 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. vLLM · Q5_K_S (current)Decode 82.77 · Prefill 438.83 ·
  2. Ollama · IQ3_XS Decode 90.69 · Prefill 447.55 ·
  3. Ollama · IQ4_XS Decode 88.03 · Prefill 388.48 ·

Core figures

Decode (avg)
82.77 tok/s
Prefill (avg)
438.83 tok/s
TTFT (avg)
2.43 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.66 GB
Power draw
178.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
Q5_K_S
Framework
vLLM
Version
v0.50
Context length
16384 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
1.05 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.6
Power draw
178.6 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 12.6 · 16384 ctx

    82.77 tok/s

    Decode

    438.83 tok/s

    Prefill

    2.43 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    178.6 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=3 running model_id=73 at Q5_K_S