← Back to community benchmarks

Qwen2.5-Coder-32B-Instruct

M1 Max (32c) · 64 GB · 8bit · 2026-03-10
Performance
4k
tokens
94.5
PP tok/s
8.7
TG tok/s
43351
TTFT (ms)
34.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 101.2 9.3 33.1 GB view
4k 94.5 8.7 34.3 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 9.3 1.00×
2× 16.0 1.72×
4× 17.6 1.89×