← Back to community benchmarks

Qwen3.5-0.8B

M2 Ultra (76c) · 128 GB · bf16 · 2026-03-09
Performance
64k
tokens
4,660
PP tok/s
83.2
TG tok/s
14065
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 128 GB
GPU Cores 76
Software
oMLX v0.2.6
macOS macOS 26.3
Context 65,536