Arao AI
Back to search results

Kimi-K3 · Q3_K_S

Start a discussion
NVIDIA RTX 4070 Ti12GBOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (Q3_K_S) on NVIDIA RTX 4070 Ti with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

101.17 tok/s

Decode

Decode speed

440.52 tok/s

Prefill

Prefill speed

1.91 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. llama.cpp · Q4_K_M Decode 95.6 · Prefill 473.23 ·
  2. Ollama · Q3_K_S (current)Decode 101.17 · Prefill 440.52 ·

Core figures

Decode (avg)
101.17 tok/s
Prefill (avg)
440.52 tok/s
TTFT (avg)
1.91 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.81 GB
Power draw
253.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
Q3_K_S
Framework
Ollama
Version
v0.26
Context length
32768 tokens
Batch size
256
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4070 Ti
Nominal VRAM
12 GB
Measured VRAM (avg)
1.05 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.4
Power draw
253.1 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

    v0.26 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    101.17 tok/s

    Decode

    440.52 tok/s

    Prefill

    1.91 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    253.1 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=42 running model_id=73 at Q3_K_S