Arao AI
Back to search results

Qwen3.6-35B-A3B · Q2_K

Start a discussion
Apple M2 UltraOllama v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q2_K) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

217.13 tok/s

Decode

Decode speed

942.96 tok/s

Prefill

Prefill speed

2.35 s

TTFT

Time to first token

42.52 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 · IQ1_S Decode 250.48 · Prefill 981.93 ·
  2. llama.cpp · Q8_0 Decode 114.98 · Prefill 558.64 ·
  3. Ollama · Q2_K (current)Decode 217.13 · Prefill 942.96 ·

Core figures

Decode (avg)
217.13 tok/s
Prefill (avg)
942.96 tok/s
TTFT (avg)
2.35 s
VRAM (avg)
42.52 GB
MTP acceptance rate
—
TTFB
1.74 GB
Power draw
119.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q2_K
Framework
Ollama
Version
v0.29
Context length
8192 tokens
Batch size
256
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
Apple M2 Ultra
Measured VRAM (avg)
42.52 GB
OS
macOS 26.1
Power draw
119.6 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

    v0.29 · macOS 26.1 · 8192 ctx

    217.13 tok/s

    Decode

    942.96 tok/s

    Prefill

    2.35 s

    TTFT

    42.52 GB

    VRAM

    —

    MTP

    119.6 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=103 running model_id=47 at Q2_K