← Back to community benchmarks

Qwen3.5-122B-A10B-oQ3.5

M3 Ultra (60c) · 96 GB · 3bit · 2026-04-01
Performance
1k
tokens
688.0
PP tok/s
42.2
TG tok/s
1488
TTFT (ms)
59.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.24
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 688.0 42.2 59.0 GB current
128k 315.5 11.4 79.2 GB view