Arao AI
Back to search results

Kimi-K3 · IQ1_S

Start a discussion
NVIDIA RTX 5070 Ti16GBvLLM v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (IQ1_S) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

131.31 tok/s

Decode

Decode speed

466.87 tok/s

Prefill

Prefill speed

2.26 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 · IQ1_S (current)Decode 131.31 · Prefill 466.87 ·
  2. vLLM · IQ3_S Decode 95.38 · Prefill 330.41 ·
  3. Strata · IQ3_S Decode 132.6 · Prefill 715.44 ·
  4. Strata · Q3_K_S Decode 129.13 · Prefill 489.23 ·

Core figures

Decode (avg)
131.31 tok/s
Prefill (avg)
466.87 tok/s
TTFT (avg)
2.26 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
1.05 GB
Power draw
234.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
IQ1_S
Framework
vLLM
Version
v0.31
Context length
32768 tokens
Batch size
16
GPU layers
999
Flash Attention
On

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)
1.05 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.4
Power draw
234.2 W

Sources & evidence

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

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

    v0.31 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx

    131.31 tok/s

    Decode

    466.87 tok/s

    Prefill

    2.26 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    234.2 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=73 at IQ1_S