← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-mxfp8

M1 Max (32c) · 64 GB · 8bit · 2026-03-10
Performance
1k
tokens
87.6
PP tok/s
10.5
TG tok/s
11691
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 87.6 10.5 27.5 GB current
4k 89.7 10.4 27.9 GB view
8k 90.4 9.9 28.3 GB view
16k 88.6 9.0 29.2 GB view
32k 83.5 7.5 30.9 GB view
Batching Results
Batch Size TG tok/s Speedup
10.5 1.00×
14.7 1.40×
12.6 1.20×
16.0 1.52×