← Back to community benchmarks

Qwen3.5-2Blm

M1 Max (32c) · 32 GB · 4bit · 2026-03-09
Performance
1k
tokens
1,263
PP tok/s
165.6
TG tok/s
811
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.2.6
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,263 165.6 3.0 GB current
4k 1,726 152.6 3.3 GB view
Batching Results
Batch Size TG tok/s Speedup
165.6 1.00×
209.9 1.27×
240.8 1.45×