← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M2 Ultra (60c) · 128 GB · 4bit · 2026-04-18
Performance
1k
tokens
910.8
PP tok/s
83.0
TG tok/s
1124
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 128 GB
GPU Cores 60
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
83.0 1.00×
130.5 1.57×