← Back to community benchmarks

Qwen3.5-0.8B

M2 (8c) · 16 GB · 8bit · 2026-03-10
Performance
4k
tokens
957.1
PP tok/s
81.8
TG tok/s
4280
TTFT (ms)
1.9
Peak mem (GB)
Hardware
Chip M2 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 956.4 85.6 1.8 GB view
4k 957.1 81.8 1.9 GB current
Batching Results
Batch Size TG tok/s Speedup
85.6 1.00×
154.0 1.80×
192.6 2.25×