Arao AI
Back to search results

Hy-Memory-30B-A3B · Q5_K_S

Start a discussion
Apple M5 Ultra512GBOllama v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Hy-Memory-30B-A3B (Q5_K_S) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

139.67 tok/s

Decode

Decode speed

562.73 tok/s

Prefill

Prefill speed

1.7 s

TTFT

Time to first token

58.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 216.9 · Prefill 866.69 ·
  2. llama.cpp · Q3_K_S Decode 189.37 · Prefill 679.35 ·
  3. Ollama · Q5_K_S (current)Decode 139.67 · Prefill 562.73 ·

Core figures

Decode (avg)
139.67 tok/s
Prefill (avg)
562.73 tok/s
TTFT (avg)
1.7 s
VRAM (avg)
58.8 GB
MTP acceptance rate
—
TTFB
1.12 GB
Power draw
133.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Hy-Memory-30B-A3B
Quantization
Q5_K_S
Framework
Ollama
Version
v0.20
Context length
4096 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
Apple M5 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
58.8 GB
OS
macOS 26.1
Power draw
133.6 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 2026-10-19

    v0.20 · macOS 26.1 · 4096 ctx

    139.67 tok/s

    Decode

    562.73 tok/s

    Prefill

    1.7 s

    TTFT

    58.8 GB

    VRAM

    —

    MTP

    133.6 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=87 at Q5_K_S