Arao AI
Back to search results

Qwen3-Coder-Next · Q2_K

Start a discussion
Apple M5 Max128GBStrata v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q2_K) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

312.25 tok/s

Decode

Decode speed

1,150.01 tok/s

Prefill

Prefill speed

2.2 s

TTFT

Time to first token

1.05 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 · Q5_K_S Decode 144.1 · Prefill 764.74 ·
  2. Strata · Q2_K (current)Decode 312.25 · Prefill 1150.01 ·

Core figures

Decode (avg)
312.25 tok/s
Prefill (avg)
1,150.01 tok/s
TTFT (avg)
2.2 s
VRAM (avg)
1.05 GB
MTP acceptance rate
0.54
TTFB
2.5 GB
Power draw
249.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q2_K
Framework
Strata
Version
v0.30
Context length
16384 tokens
Batch size
256
GPU layers
15
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)
1.05 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.6
Power draw
249.7 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

    v0.30 · Ubuntu 22.04 · CUDA 12.6 · 16384 ctx

    312.25 tok/s

    Decode

    1,150.01 tok/s

    Prefill

    2.2 s

    TTFT

    1.05 GB

    VRAM

    0.54

    MTP

    249.7 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=28 running model_id=58 at Q2_K