← Back to community benchmarks

Qwen3.5-0.8B

M4 (10c) · 32 GB · unknown · 2026-03-12
Performance
1k
tokens
1,439
PP tok/s
13.4
TG tok/s
711
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.9
macOS macOS 15.7.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,439 13.4 3.3 GB current
4k 1,703 13.2 3.4 GB view
Batching Results
Batch Size TG tok/s Speedup
13.4 1.00×
25.6 1.91×
48.7 3.63×