← 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
64k
tokens
1,139
PP tok/s
62.5
TG tok/s
57555
TTFT (ms)
26.0
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 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,944 85.5 19.9 GB view
4k 2,055 84.5 20.7 GB view
8k 1,995 82.7 21.1 GB view
16k 1,843 78.1 21.9 GB view
32k 1,573 70.6 23.7 GB view
64k 1,139 62.5 26.0 GB current
Batching Results
Batch Size TG tok/s Speedup
85.5 1.00×
142.5 1.67×
365.6 4.28×