← Back to community benchmarks

Qwen3___5-0___8B

M4 (10c) · 16 GB · 8bit · 2026-03-09
Performance
4k
tokens
2,158
PP tok/s
103.7
TG tok/s
1898
TTFT (ms)
1.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,213 112.1 1.8 GB view
4k 2,158 103.7 1.9 GB current
8k 2,144 96.5 2.0 GB view
16k 1,901 83.9 2.4 GB view
Batching Results
Batch Size TG tok/s Speedup
112.1 1.00×
111.8 1.00×
315.0 2.81×
327.5 2.92×