← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Ultra (48c) · 128 GB · 4bit · 2026-04-17
Performance
8k
tokens
858.5
PP tok/s
60.3
TG tok/s
9542
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 128 GB
GPU Cores 48
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 651.6 69.8 19.2 GB view
4k 840.6 64.5 20.0 GB view
8k 858.5 60.3 20.4 GB current
16k 835.1 54.2 21.0 GB view
Batching Results
Batch Size TG tok/s Speedup
69.8 1.00×
110.1 1.58×
150.6 2.16×
189.9 2.72×