← Back to community benchmarks

Qwen3.5-35B-A3BIQ4_M

M4 Pro (16c) · 48 GB · 4bit · 2026-04-13
Performance
8k
tokens
739.6
PP tok/s
43.1
TG tok/s
11076
TTFT (ms)
23.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.4
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 635.0 47.3 22.2 GB view
4k 753.6 45.2 22.9 GB view
8k 739.6 43.1 23.3 GB current
Batching Results
Batch Size TG tok/s Speedup
47.3 1.00×
122.7 2.59×