Arao AI
Back to search results

Qwen3.8-9B · IQ3_XS

Start a discussion
Apple M5 Max128GBStrata v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_XS) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

320.14 tok/s

Decode

Decode speed

1,058.22 tok/s

Prefill

Prefill speed

1.58 s

TTFT

Time to first token

13.82 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · Q3_K_L Decode 202.52 · Prefill 1021.73 ·
  2. Strata · Q3_K_M Decode 280.05 · Prefill 1450.84 ·
  3. Strata · IQ3_XS (current)Decode 320.14 · Prefill 1058.22 ·
  4. Strata · Q2_K Decode 331.24 · Prefill 1237.62 ·

Core figures

Decode (avg)
320.14 tok/s
Prefill (avg)
1,058.22 tok/s
TTFT (avg)
1.58 s
VRAM (avg)
13.82 GB
MTP acceptance rate
0.77
TTFB
2.56 GB
Power draw
39.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ3_XS
Framework
Strata
Version
v0.35
Context length
2048 tokens
Batch size
256
GPU layers
12
Flash Attention
On

Hardware

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

GPU
Apple M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
13.82 GB
OS
macOS 15.0
Driver
Apple M5 Max
CUDA
N/A
Power draw
39.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.35 · macOS 15.0 · CUDA N/A · 2048 ctx

    320.14 tok/s

    Decode

    1,058.22 tok/s

    Prefill

    1.58 s

    TTFT

    13.82 GB

    VRAM

    0.77

    MTP

    39.6 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=28 running model_id=52 at IQ3_XS