← Back to community benchmarks

Qwen2.5-Coder-32B-Instruct

M2 Max (38c) · 64 GB · 4bit · 2026-03-10
Performance
4k
tokens
48.0
PP tok/s
4.4
TG tok/s
85387
TTFT (ms)
19.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 48.1 5.8 17.9 GB view
4k 48.0 4.4 19.5 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 5.8 1.00×
2× 6.1 1.05×
4× 6.6 1.14×