← Back to community benchmarks

Qwen3.5-122B-A10B6.5bit

M4 Max (40c) · 128 GB · 6bit · 2026-03-17

Performance

4k

tokens

375.4

PP tok/s

40.5

TG tok/s

10911

TTFT (ms)

95.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.18

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	296.8	39.8	94.0 GB	view
4k	375.4	40.5	95.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	39.8	1.00×
2×	64.1	1.61×
4×	60.0	1.51×