← Back to community benchmarks

Qwen3.5-0.8Blm

M1 Max (32c) · 64 GB · 4bit · 2026-04-05

Performance

4k

tokens

2,772

PP tok/s

214.0

TG tok/s

1478

TTFT (ms)

1.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,711	240.0	1.6 GB	view
4k	2,772	214.0	1.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	240.0	1.00×
2×	337.1	1.40×
4×	427.5	1.78×