Arao AI
Back to search results

Kimi-K3 · Q2_K

Start a discussion
AMD Radeon RX 907016GBOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (Q2_K) on AMD Radeon RX 9070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

125.3 tok/s

Decode

Decode speed

531.07 tok/s

Prefill

Prefill speed

1.15 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 · IQ4_XS Decode 102.59 · Prefill 523.94 ·
  2. vLLM · Q3_K_M Decode 122.09 · Prefill 529.79 ·
  3. Ollama · IQ3_XS Decode 117.33 · Prefill 604.75 ·
  4. Ollama · Q2_K (current)Decode 125.3 · Prefill 531.07 ·

Core figures

Decode (avg)
125.3 tok/s
Prefill (avg)
531.07 tok/s
TTFT (avg)
1.15 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
1 GB
Power draw
256.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
Q2_K
Framework
Ollama
Version
v0.26
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
AMD Radeon RX 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
1.05 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.4
Power draw
256.2 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

    v0.26 · Ubuntu 22.04 · CUDA 12.4 · 8192 ctx

    125.3 tok/s

    Decode

    531.07 tok/s

    Prefill

    1.15 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    256.2 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=21 running model_id=73 at Q2_K