Arao AI
Back to search results

Qwen3.8-9B · Q5_K_S

Start a discussion
Apple M1 MaxOllama v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q5_K_S) on Apple M1 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

62.86 tok/s

Decode

Decode speed

246.16 tok/s

Prefill

Prefill speed

1.21 s

TTFT

Time to first token

19.11 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 · IQ3_S Decode 82.95 · Prefill 300.79 ·
  2. llama.cpp · Q4_K_S Decode 83.02 · Prefill 308.94 ·
  3. Ollama · Q2_K Decode 100.43 · Prefill 476.64 ·
  4. Ollama · Q5_K_S (current)Decode 62.86 · Prefill 246.16 ·

Core figures

Decode (avg)
62.86 tok/s
Prefill (avg)
246.16 tok/s
TTFT (avg)
1.21 s
VRAM (avg)
19.11 GB
MTP acceptance rate
—
TTFB
0.5 GB
Power draw
35.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q5_K_S
Framework
Ollama
Version
v0.49
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
Apple M1 Max
Measured VRAM (avg)
19.11 GB
OS
macOS 15.0
Driver
Apple M1 Max
CUDA
N/A
Power draw
35.9 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

    v0.49 · macOS 15.0 · CUDA N/A · 8192 ctx

    62.86 tok/s

    Decode

    246.16 tok/s

    Prefill

    1.21 s

    TTFT

    19.11 GB

    VRAM

    —

    MTP

    35.9 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=101 running model_id=52 at Q5_K_S