← Back to community benchmarks

DeepSeek-R1-Distill-Qwen-7B

M2 Max (30c) · 32 GB · 4bit · 2026-04-28
Performance
4k
tokens
586.3
PP tok/s
65.7
TG tok/s
6993
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 558.0 73.1 4.8 GB view
4k 586.3 65.7 4.9 GB current
Batching Results
Batch Size TG tok/s Speedup
73.1 1.00×
103.9 1.42×
112.0 1.53×