← Back to community benchmarks

Qwen3.5-2B

M4 (8c) · 16 GB · 6bit · 2026-03-11
Performance
4k
tokens
780.4
PP tok/s
59.0
TG tok/s
5249
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 778.5 60.6 2.9 GB view
4k 780.4 59.0 3.0 GB current
Batching Results
Batch Size TG tok/s Speedup
60.6 1.00×
89.4 1.48×
93.2 1.54×