Arao AI
Back to search results

Kimi-K3 · Q5_K_M

Start a discussion
NVIDIA RTX 408016GBOllama v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (Q5_K_M) on NVIDIA RTX 4080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

91.51 tok/s

Decode

Decode speed

334.92 tok/s

Prefill

Prefill speed

0.65 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 Decode 139.12 · Prefill 753.5 ·
  2. Ollama · Q5_K_M (current)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)
91.51 tok/s
Prefill (avg)
334.92 tok/s
TTFT (avg)
0.65 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.73 GB
Power draw
284.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
Q5_K_M
Framework
Ollama
Version
v0.49
Context length
32768 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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 22.04
Driver
565.57
CUDA
12.4
Power draw
284.5 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

    v0.49 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    91.51 tok/s

    Decode

    334.92 tok/s

    Prefill

    0.65 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    284.5 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=41 running model_id=73 at Q5_K_M