Arao AI
Back to search results

Raon-1-mini-preview · IQ2_XS

Start a discussion
Apple M5 Max128GBllama.cpp v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Raon-1-mini-preview (IQ2_XS) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

103.96 tok/s

Decode

Decode speed

353.6 tok/s

Prefill

Prefill speed

1.49 s

TTFT

Time to first token

31.13 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

13 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS (current)Decode 103.96 · Prefill 353.6 ·
  2. llama.cpp · IQ4_XS Decode 86.99 · Prefill 341.88 ·
  3. Ollama · IQ1_S Decode 109.91 · Prefill 383.57 ·
  4. Ollama · Q5_K_S Decode 61.49 · Prefill 244.43 ·

Core figures

Decode (avg)
103.96 tok/s
Prefill (avg)
353.6 tok/s
TTFT (avg)
1.49 s
VRAM (avg)
31.13 GB
MTP acceptance rate
—
TTFB
0.83 GB
Power draw
66.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Raon-1-mini-preview
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.28
Context length
16384 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
Apple M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
31.13 GB
OS
macOS 26.1
Power draw
66.4 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-22

    v0.28 · macOS 26.1 · 16384 ctx

    103.96 tok/s

    Decode

    353.6 tok/s

    Prefill

    1.49 s

    TTFT

    31.13 GB

    VRAM

    —

    MTP

    66.4 W

    Power draw

    L2 batch seed 2026-10-22: llama.cpp on hw_id=28 running model_id=93 at IQ2_XS