← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-29
Performance
1k
tokens
2,248
PP tok/s
230.1
TG tok/s
456
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,248 230.1 36.7 GB current
8k 1,532 330.0 37.9 GB view
32k 902.4 193.1 39.8 GB view
128k 290.2 80.5 46.3 GB view