← Back to community benchmarks

DeepSeek-R1-0528-Qwen3-8B

M1 Max (32c) · 64 GB · 4bit · 2026-05-15
Performance
1k
tokens
304.4
PP tok/s
56.1
TG tok/s
3364
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.0.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 304.4 56.1 5.0 GB current
4k 307.3 46.6 5.7 GB view
8k 291.2 37.7 6.6 GB view
16k 260.6 27.4 8.3 GB view
Batching Results
Batch Size TG tok/s Speedup
56.1 1.00×
66.0 1.18×
72.7 1.30×
64.7 1.15×