← Back to community benchmarks

Qwen3.5-2B

M1 (7c) · 8 GB · 6bit · 2026-03-13
Performance
4k
tokens
301.1
PP tok/s
28.7
TG tok/s
13605
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 8 GB
GPU Cores 7
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 310.0 32.2 2.9 GB view
4k 301.1 28.7 3.0 GB current
Batching Results
Batch Size TG tok/s Speedup
32.2 1.00×
42.2 1.31×
41.7 1.30×