← Back to community benchmarks

Qwen3.5-27B-heretic-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-15
Performance
64k
tokens
543.5
PP tok/s
18.7
TG tok/s
120586
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 769.0 32.2 16.3 GB view
4k 891.1 31.2 17.7 GB view
8k 864.3 30.3 18.4 GB view
16k 761.0 28.3 19.6 GB view
32k 682.3 25.4 22.1 GB view
64k 543.5 18.7 27.1 GB current
Batching Results
Batch Size TG tok/s Speedup
32.2 1.00×
45.7 1.42×
56.2 1.75×