← Back to community benchmarks

Qwen3.5-35B-A3Blm

M1 Pro (14c) · 32 GB · 4bit · 2026-03-10
Performance
4k
tokens
263.6
PP tok/s
41.5
TG tok/s
15539
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.2.7
macOS macOS 15.6
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 239.2 43.7 18.3 GB view
4k 263.6 41.5 18.4 GB current
8k 260.9 36.4 18.6 GB view
Batching Results
Batch Size TG tok/s Speedup
43.7 1.00×
52.0 1.19×
58.1 1.33×