← Back to community benchmarks

Qwen3.5-4B9bit

M4 (10c) · 16 GB · 8bit · 2026-05-15
Performance
1k
tokens
373.0
PP tok/s
20.5
TG tok/s
2745
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 373.0 20.5 5.4 GB current
4k 391.7 20.0 6.1 GB view