Arao AI
Back to search results

Kimi-K3 · IQ3_XS

Start a discussion
NVIDIA RTX 408016GBOllama v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (IQ3_XS) on NVIDIA RTX 4080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

139.12 tok/s

Decode

Decode speed

753.5 tok/s

Prefill

Prefill speed

1.42 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 · IQ3_XS (current)Decode 139.12 · Prefill 753.5 ·
  2. Ollama · Q5_K_M Decode 91.51 · Prefill 334.92 ·
  3. Strata · FP16 Decode 79.66 · Prefill 266.23 ·
  4. Strata · Q4_K_M Decode 165.81 · Prefill 742.77 ·

Core figures

Decode (avg)
139.12 tok/s
Prefill (avg)
753.5 tok/s
TTFT (avg)
1.42 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
1.11 GB
Power draw
297.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
IQ3_XS
Framework
Ollama
Version
v0.31
Context length
32768 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4080
Nominal VRAM
16 GB
Measured VRAM (avg)
1.05 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
13.0
Power draw
297.6 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

    v0.31 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx

    139.12 tok/s

    Decode

    753.5 tok/s

    Prefill

    1.42 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    297.6 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=41 running model_id=73 at IQ3_XS