← Back to community benchmarks

Qwen3.5-0.8B

M1 (8c) · 8 GB · 8bit · 2026-03-10
Performance
8k
tokens
813.7
PP tok/s
7.2
TG tok/s
10068
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 8 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 845.0 62.7 1.8 GB view
4k 834.2 56.6 1.9 GB view
8k 813.7 7.2 4.0 GB current
Batching Results
Batch Size TG tok/s Speedup
62.7 1.00×
31.9 0.51×
58.5 0.93×