← Back to community benchmarks

Qwen3.5-0.8B

M1 Max (24c) · 64 GB · 8bit · 2026-03-10
Performance
4k
tokens
2,320
PP tok/s
179.9
TG tok/s
1765
TTFT (ms)
2.2
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,290 200.2 2.0 GB view
4k 2,320 179.9 2.2 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 200.2 1.00×
2× 204.5 1.02×
4× 344.1 1.72×