← Back to community benchmarks

qwen3-8b

M1 (7c) · 8 GB · 6bit · 2026-03-09
Performance
4k
tokens
264.3
PP tok/s
23.3
TG tok/s
15497
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 8 GB
GPU Cores 7
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 266.7 24.6 2.9 GB view
4k 264.3 23.3 3.0 GB current
Batching Results
Batch Size TG tok/s Speedup
24.6 1.00×
37.2 1.51×
35.6 1.45×