Arao AI
Back to search results

Kimi-K3 · IQ3_XS

Start a discussion
AMD Radeon RX 9070 XT16GBllama.cpp v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (IQ3_XS) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

118.99 tok/s

Decode

Decode speed

614.09 tok/s

Prefill

Prefill speed

0.95 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. llama.cpp · IQ3_XS (current)Decode 118.99 · Prefill 614.09 ·
  2. llama.cpp · Q5_K_M Decode 84.68 · Prefill 344.07 ·
  3. vLLM · IQ4_XS Decode 107.13 · Prefill 359.17 ·

Core figures

Decode (avg)
118.99 tok/s
Prefill (avg)
614.09 tok/s
TTFT (avg)
0.95 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.95 GB
Power draw
229.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
IQ3_XS
Framework
llama.cpp
Version
v0.54
Context length
2048 tokens
Batch size
512
GPU layers
99
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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
1.05 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
12.6
Power draw
229.7 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

    v0.54 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    118.99 tok/s

    Decode

    614.09 tok/s

    Prefill

    0.95 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    229.7 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=16 running model_id=73 at IQ3_XS