Arao AI
Back to search results

Kimi-K3 · IQ4_XS

Start a discussion
AMD Radeon RX 907016GBvLLM v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (IQ4_XS) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

102.59 tok/s

Decode

Decode speed

523.94 tok/s

Prefill

Prefill speed

1.46 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 (current)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 Decode 125.3 · Prefill 531.07 ·

Core figures

Decode (avg)
102.59 tok/s
Prefill (avg)
523.94 tok/s
TTFT (avg)
1.46 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.82 GB
Power draw
221.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
IQ4_XS
Framework
vLLM
Version
v0.45
Context length
16384 tokens
Batch size
8
GPU layers
999
Flash Attention
On

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-pro 24.20
CUDA
12.8
Power draw
221.4 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

    v0.45 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx

    102.59 tok/s

    Decode

    523.94 tok/s

    Prefill

    1.46 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    221.4 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=21 running model_id=73 at IQ4_XS