← Back to community benchmarks

Qwen3___5-4B

M4 (10c) · 16 GB · 4bit · 2026-03-09
Performance
32k
tokens
320.7
PP tok/s
23.5
TG tok/s
102161
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 407.8 39.2 3.9 GB view
4k 404.3 37.1 4.2 GB view
8k 388.7 34.5 4.6 GB view
16k 362.8 30.2 4.8 GB view
32k 320.7 23.5 5.9 GB current
64k 257.2 16.4 8.0 GB view
Batching Results
Batch Size TG tok/s Speedup
39.2 1.00×
75.4 1.92×
94.2 2.40×