← Back to community benchmarks

Qwen3.5-0.8B

M1 Max (32c) · 64 GB · 8bit · 2026-03-11
Performance
1k
tokens
3,199
PP tok/s
195.4
TG tok/s
320
TTFT (ms)
2.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.7
macOS macOS 26.2
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 195.4 1.00×
2× 331.8 1.70×
4× 436.6 2.23×
8× 501.2 2.56×