Arao AI
Back to search results

Qwen3.6-35B-A3B · Q5_K_S

Start a discussion
Apple M5 Ultra512GBllama.cpp v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q5_K_S) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

169.24 tok/s

Decode

Decode speed

662.43 tok/s

Prefill

Prefill speed

0.8 s

TTFT

Time to first token

68.25 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_S (current)Decode 169.24 · Prefill 662.43 ·
  2. Ollama · Q3_K_M Decode 206.74 · Prefill 725.54 ·

Core figures

Decode (avg)
169.24 tok/s
Prefill (avg)
662.43 tok/s
TTFT (avg)
0.8 s
VRAM (avg)
68.25 GB
MTP acceptance rate
—
TTFB
1.35 GB
Power draw
136.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.38
Context length
8192 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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)
68.25 GB
OS
macOS 26.1
Power draw
136.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.38 · macOS 26.1 · 8192 ctx

    169.24 tok/s

    Decode

    662.43 tok/s

    Prefill

    0.8 s

    TTFT

    68.25 GB

    VRAM

    —

    MTP

    136.6 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=29 running model_id=47 at Q5_K_S