← Back to community benchmarks

Qwen3.5-0.8B

M1 (8c) · 16 GB · 8bit · 2026-03-10
Performance
1k
tokens
676.8
PP tok/s
46.9
TG tok/s
1513
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 676.8 46.9 1.8 GB current
16k 585.9 33.7 2.4 GB view
64k 353.7 18.6 4.4 GB view
Batching Results
Batch Size TG tok/s Speedup
46.9 1.00×
76.9 1.64×
113.7 2.42×