← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr2e7

M5 Max (40c) · 128 GB · 8bit · 2026-03-17
Performance
1k
tokens
2,053
PP tok/s
89.0
TG tok/s
499
TTFT (ms)
32.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.14
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,053 89.0 32.6 GB current
4k 2,473 75.9 33.1 GB view
Batching Results
Batch Size TG tok/s Speedup
89.0 1.00×
126.9 1.43×
172.3 1.94×