← Back to community benchmarks

Qwen3.5-35B-A3B-GPTQ-Int4

M1 Ultra (48c) · 64 GB · 4bit · 2026-04-15
Performance
1k
tokens
733.1
PP tok/s
55.7
TG tok/s
1397
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 64 GB
GPU Cores 48
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 733.1 55.7 21.6 GB current
4k 920.5 52.6 22.3 GB view
Batching Results
Batch Size TG tok/s Speedup
55.7 1.00×
44.2 0.79×
80.7 1.45×