← Back to community benchmarks

Qwen3.5-0.8B9bit

M3 Ultra (60c) · 96 GB · 8bit · 2026-03-09
Performance
1k
tokens
2,898
PP tok/s
301.0
TG tok/s
353
TTFT (ms)
1.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,898 301.0 1.9 GB current
64k 4,818 122.4 4.3 GB view
Batching Results
Batch Size TG tok/s Speedup
301.0 1.00×
508.5 1.69×
745.7 2.48×
1070.8 3.56×