← Back to community benchmarks

Qwen3.5-0.8B

M2 (10c) · 8 GB · unknown · 2026-03-10
Performance
1k
tokens
1,008
PP tok/s
11.1
TG tok/s
1016
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 8 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
11.1 1.00×
18.7 1.68×
20.9 1.88×