← Back to community benchmarks

Qwen3.5-4B

M3 Max (40c) · 128 GB · bf16 · 2026-03-12
Performance
1k
tokens
1,346
PP tok/s
40.5
TG tok/s
761
TTFT (ms)
9.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.8
macOS macOS 15.6.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 40.5 1.00×
2× 39.0 0.96×
4× 75.0 1.85×
8× 142.1 3.51×