← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-hermes-oQ4-fp16-mtp

M2 Ultra (60c) · 64 GB · 4bit · 2026-07-23
Performance
1k
tokens
1,968
PP tok/s
85.7
TG tok/s
520
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,968 85.7 19.9 GB current
4k 2,060 83.3 20.7 GB view
8k 1,979 81.2 21.0 GB view
16k 1,835 77.8 21.8 GB view
32k 1,579 74.2 23.3 GB view
64k 1,153 63.4 25.7 GB view
Batching Results
Batch Size TG tok/s Speedup
85.7 1.00×
143.5 1.67×
365.5 4.26×