← Back to community benchmarks

Qwen3.5-0.8Blm

M1 Max (32c) · 64 GB · 4bit · 2026-04-05
Performance
1k
tokens
1,723
PP tok/s
240.4
TG tok/s
594
TTFT (ms)
1.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.4
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,723 240.4 1.6 GB current
4k 2,721 216.7 1.7 GB view
Batching Results
Batch Size TG tok/s Speedup
240.4 1.00×
337.2 1.40×
428.4 1.78×
499.4 2.08×