← Back to community benchmarks

Qwen3.6-35B-A3Bmxfp8

M1 Max (24c) · 64 GB · 8bit · 2026-04-18
Performance
1k
tokens
398.4
PP tok/s
48.1
TG tok/s
2570
TTFT (ms)
34.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.6
macOS macOS 26.1
Context 1,024