Arao AI
Back to search results

Raon-1-mini-preview · Q4_K_M

Start a discussion
Apple M2 UltraOllama v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Raon-1-mini-preview (Q4_K_M) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

110.45 tok/s

Decode

Decode speed

501.39 tok/s

Prefill

Prefill speed

0.35 s

TTFT

Time to first token

51.69 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_M Decode 155.94 · Prefill 578.17 ·
  2. llama.cpp · IQ3_S Decode 130 · Prefill 684.42 ·
  3. Ollama · Q4_K_M (current)Decode 110.45 · Prefill 501.39 ·

Core figures

Decode (avg)
110.45 tok/s
Prefill (avg)
501.39 tok/s
TTFT (avg)
0.35 s
VRAM (avg)
51.69 GB
MTP acceptance rate
—
TTFB
0.88 GB
Power draw
119.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Raon-1-mini-preview
Quantization
Q4_K_M
Framework
Ollama
Version
v0.38
Context length
32768 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Apple M2 Ultra
Measured VRAM (avg)
51.69 GB
OS
macOS 26.1
Power draw
119.1 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

    v0.38 · macOS 26.1 · 32768 ctx

    110.45 tok/s

    Decode

    501.39 tok/s

    Prefill

    0.35 s

    TTFT

    51.69 GB

    VRAM

    —

    MTP

    119.1 W

    Power draw

    L2 batch seed 2026-10-22: Ollama on hw_id=103 running model_id=93 at Q4_K_M