Arao AI
Back to search results

Kimi-K3 · IQ1_S

Start a discussion
AMD Radeon RX 7900 XTX24GBllama.cpp v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (IQ1_S) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

109.82 tok/s

Decode

Decode speed

547.49 tok/s

Prefill

Prefill speed

2.4 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 · IQ1_S (current)Decode 109.82 · Prefill 547.49 ·
  2. llama.cpp · Q3_K_L Decode 75 · Prefill 318.12 ·
  3. Ollama · Q5_K_S Decode 56.93 · Prefill 285.15 ·

Core figures

Decode (avg)
109.82 tok/s
Prefill (avg)
547.49 tok/s
TTFT (avg)
2.4 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.88 GB
Power draw
248.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.27
Context length
8192 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 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
1.05 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
12.6
Power draw
248.5 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

    v0.27 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx

    109.82 tok/s

    Decode

    547.49 tok/s

    Prefill

    2.4 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    248.5 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=11 running model_id=73 at IQ1_S