← Back to community benchmarks

qwen35-27b

M4 Max (32c) · 36 GB · 4bit · 2026-03-14
Performance
8k
tokens
199.4
PP tok/s
20.7
TG tok/s
41087
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 8,192