← Back to community benchmarks

Qwen3.5-4B

M3 Ultra (80c) · 256 GB · 8bit · 2026-03-10
Performance
1k
tokens
2,527
PP tok/s
109.7
TG tok/s
405
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 256 GB
GPU Cores 80
Software
oMLX v0.2.7
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,527 109.7 5.9 GB current
4k 2,595 104.1 6.1 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 109.7 1.00×
2× 192.5 1.75×
4× 281.2 2.56×
8× 372.9 3.40×