← Back to community benchmarks

Jackrong:Qwen3.5-9B-GLM5.1-Distill-v1-oQ4-mtp--最新

M4 (10c) · 16 GB · 4bit · 2026-05-12

Performance

4k

tokens

221.7

PP tok/s

27.9

TG tok/s

18475

TTFT (ms)

6.6

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	215.3	29.9	6.0 GB	view
4k	221.7	27.9	6.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	29.9	1.00×
2×	38.3	1.28×
4×	129.9	4.34×