← Back to community benchmarks

Qwen3.5-4B

M3 Ultra (80c) · 256 GB · 4bit · 2026-03-10
Performance
1k
tokens
2,578
PP tok/s
161.9
TG tok/s
397
TTFT (ms)
4.0
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 2,578 161.9 4.0 GB current
4k 2,613 150.5 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
161.9 1.00×
277.5 1.71×
384.2 2.37×
515.0 3.18×