← Back to community benchmarks

Qwen3.5-0.8B

M2 Ultra (76c) · 192 GB · 4bit · 2026-03-09
Performance
64k
tokens
3,903
PP tok/s
85.6
TG tok/s
16793
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.2.6
macOS macOS 15.0
Context 65,536