← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · bf16 · 2026-03-11
Performance
4k
tokens
206.8
PP tok/s
6.4
TG tok/s
19804
TTFT (ms)
9.5
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 193.4 6.2 9.3 GB view
4k 206.8 6.4 9.5 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 6.2 1.00×
2× 6.6 1.06×
4× 13.2 2.13×