← Back to community benchmarks

Qwen3.5-27B

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-10
Performance
1k
tokens
423.4
PP tok/s
35.7
TG tok/s
2418
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 423.4 35.7 16.6 GB current
4k 429.2 34.0 17.0 GB view
8k 423.5 32.5 17.4 GB view
16k 409.8 29.7 18.3 GB view
32k 383.4 25.4 20.1 GB view
Batching Results
Batch Size TG tok/s Speedup
35.7 1.00×
65.1 1.82×
89.3 2.50×
102.9 2.88×