← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M5 Max (40c) · 128 GB · 5bit · 2026-03-28

Performance

8k

tokens

1,487

PP tok/s

44.1

TG tok/s

5509

TTFT (ms)

83.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.24

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,170	47.9	81.8 GB	view
4k	1,522	45.4	83.3 GB	view
8k	1,487	44.1	83.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	47.9	1.00×
2×	74.5	1.56×
4×	91.4	1.91×