Arao AI
Back to search results

Qwen3-8B · Q5_K_M

Start a discussion
Apple M1 ProStrata v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_M) on Apple M1 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

74.46 tok/s

Decode

Decode speed

397.25 tok/s

Prefill

Prefill speed

1.94 s

TTFT

Time to first token

17.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · FP16 Decode 33.62 · Prefill 122.03 ·
  2. llama.cpp · Q5_K_M Decode 60.3 · Prefill 277.54 ·
  3. Strata · Q5_K_M (current)Decode 74.46 · Prefill 397.25 ·

Core figures

Decode (avg)
74.46 tok/s
Prefill (avg)
397.25 tok/s
TTFT (avg)
1.94 s
VRAM (avg)
17.72 GB
MTP acceptance rate
0.5
TTFB
0.6 GB
Power draw
59.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q5_K_M
Framework
Strata
Version
v0.34
Context length
32768 tokens
Batch size
1024
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 M1 Pro
Measured VRAM (avg)
17.72 GB
OS
macOS 15.0
Driver
Apple M1 Pro
CUDA
N/A
Power draw
59.8 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

    v0.34 · macOS 15.0 · CUDA N/A · 32768 ctx

    74.46 tok/s

    Decode

    397.25 tok/s

    Prefill

    1.94 s

    TTFT

    17.72 GB

    VRAM

    0.5

    MTP

    59.8 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=100 running model_id=53 at Q5_K_M