← Back to community benchmarks

Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliteratedoQ8-mtp

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-18
Performance
4k
tokens
2,071
PP tok/s
81.1
TG tok/s
1978
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,421 82.7 35.4 GB view
4k 2,071 81.1 36.2 GB current
Batching Results
Batch Size TG tok/s Speedup
82.7 1.00×
137.7 1.67×
203.9 2.47×