Arao AI
Back to search results

Qwen3.8-9B · Q4_K_M

Start a discussion
Apple M2 UltraStrata v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on Apple M2 Ultra with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

129.12 tok/s

Decode

Decode speed

454.27 tok/s

Prefill

Prefill speed

0.12 s

TTFT

Time to first token

17.6 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · IQ1_S Decode 152.06 · Prefill 546.19 ·
  2. Strata · Q4_K_M (current)Decode 129.12 · Prefill 454.27 ·
  3. Strata · Q8_0 Decode 89.33 · Prefill 303.19 ·

Core figures

Decode (avg)
129.12 tok/s
Prefill (avg)
454.27 tok/s
TTFT (avg)
0.12 s
VRAM (avg)
17.6 GB
MTP acceptance rate
0.55
TTFB
1.03 GB
Power draw
49.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q4_K_M
Framework
Strata
Version
v0.37
Context length
32768 tokens
Batch size
256
GPU layers
8
Flash Attention
Off

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)
17.6 GB
OS
macOS 15.0
Driver
Apple M2 Ultra
CUDA
N/A
Power draw
49.1 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.37 · macOS 15.0 · CUDA N/A · 32768 ctx

    129.12 tok/s

    Decode

    454.27 tok/s

    Prefill

    0.12 s

    TTFT

    17.6 GB

    VRAM

    0.55

    MTP

    49.1 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=103 running model_id=52 at Q4_K_M