← Back to community benchmarks

Qwen3.5-0.8B

M1 Max (32c) · 64 GB · 8bit · 2026-03-19
Performance
4k
tokens
3,359
PP tok/s
179.4
TG tok/s
1219
TTFT (ms)
2.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.19
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,166 200.4 2.0 GB view
4k 3,359 179.4 2.3 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 200.4 1.00×
2× 354.6 1.77×
4× 492.5 2.46×