Arao AI
Back to search results

Qwen3.8-9B · Q3_K_S

Start a discussion
Apple M5 Pro64GBOllama v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_S) on Apple M5 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

144.08 tok/s

Decode

Decode speed

671.77 tok/s

Prefill

Prefill speed

0.84 s

TTFT

Time to first token

14.38 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 · IQ3_S Decode 158.08 · Prefill 657.93 ·
  2. vLLM · Q2_K Decode 169.33 · Prefill 690.81 ·
  3. Ollama · IQ3_S Decode 136.51 · Prefill 597.98 ·
  4. Ollama · Q3_K_S (current)Decode 144.08 · Prefill 671.77 ·

Core figures

Decode (avg)
144.08 tok/s
Prefill (avg)
671.77 tok/s
TTFT (avg)
0.84 s
VRAM (avg)
14.38 GB
MTP acceptance rate
—
TTFB
1.15 GB
Power draw
94 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q3_K_S
Framework
Ollama
Version
v0.47
Context length
8192 tokens
Batch size
512
GPU layers
20
Flash Attention
On

Hardware

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

GPU
Apple M5 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
14.38 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
94 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

    v0.47 · macOS 15.0 · CUDA N/A · 8192 ctx

    144.08 tok/s

    Decode

    671.77 tok/s

    Prefill

    0.84 s

    TTFT

    14.38 GB

    VRAM

    —

    MTP

    94 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=27 running model_id=52 at Q3_K_S