← Back to community benchmarks

Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled

M2 Ultra (76c) · 192 GB · bf16 · 2026-03-11

Performance

64k

tokens

4,230

PP tok/s

78.8

TG tok/s

15494

TTFT (ms)

4.9

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