Arao AI
Back to search results

Kimi-K3 · Q3_K_M

Start a discussion
AMD Radeon RX 907016GBvLLM v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (Q3_K_M) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

122.09 tok/s

Decode

Decode speed

529.79 tok/s

Prefill

Prefill speed

1.01 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 (current)Decode 122.09 · Prefill 529.79 ·
  3. Ollama · IQ3_XS Decode 117.33 · Prefill 604.75 ·
  4. Ollama · Q2_K Decode 125.3 · Prefill 531.07 ·

Core figures

Decode (avg)
122.09 tok/s
Prefill (avg)
529.79 tok/s
TTFT (avg)
1.01 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.98 GB
Power draw
269.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
Q3_K_M
Framework
vLLM
Version
v0.27
Context length
32768 tokens
Batch size
32
GPU layers
999
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
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
12.4
Power draw
269.2 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

    v0.27 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx

    122.09 tok/s

    Decode

    529.79 tok/s

    Prefill

    1.01 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    269.2 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=21 running model_id=73 at Q3_K_M