← Back to community benchmarks

Qwen3.5-27B-TurboQuant

M4 (8c) · 16 GB · 2bit · 2026-04-18
Performance
1k
tokens
46.2
PP tok/s
10.3
TG tok/s
22149
TTFT (ms)
9.6
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 46.2 10.3 9.6 GB current
4k 38.6 8.2 10.9 GB view
Batching Results
Batch Size TG tok/s Speedup
10.3 1.00×
8.4 0.82×
4.2 0.41×