Arao AI
Back to search results

Qwen3-1.7B · Q5_K_S

Start a discussion
Apple M3 Max36GBStrata v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q5_K_S) on Apple M3 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

239.13 tok/s

Decode

Decode speed

849.25 tok/s

Prefill

Prefill speed

1.36 s

TTFT

Time to first token

5.31 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ2_XS Decode 309.15 · Prefill 1109.54 ·
  2. vLLM · Q3_K_L Decode 226.47 · Prefill 1116.37 ·
  3. Ollama · FP16 Decode 96.85 · Prefill 510.37 ·
  4. Ollama · IQ4_XS Decode 188.36 · Prefill 704.89 ·
  5. Strata · Q5_K_S (current)Decode 239.13 · Prefill 849.25 ·

Core figures

Decode (avg)
239.13 tok/s
Prefill (avg)
849.25 tok/s
TTFT (avg)
1.36 s
VRAM (avg)
5.31 GB
MTP acceptance rate
0.46
TTFB
1.91 GB
Power draw
62.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q5_K_S
Framework
Strata
Version
v0.31
Context length
4096 tokens
Batch size
1024
GPU layers
12
Flash Attention
Off

Hardware

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

GPU
Apple M3 Max
Nominal VRAM
36 GB
Measured VRAM (avg)
5.31 GB
OS
macOS 15.0
Driver
Apple M3 Max
CUDA
N/A
Power draw
62.4 W

Sources & evidence

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

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

    v0.31 · macOS 15.0 · CUDA N/A · 4096 ctx

    239.13 tok/s

    Decode

    849.25 tok/s

    Prefill

    1.36 s

    TTFT

    5.31 GB

    VRAM

    0.46

    MTP

    62.4 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=4 running model_id=55 at Q5_K_S