← Back to community benchmarks
Qwen3.5-0.8B
Performance
64k
tokens
3,586
PP tok/s
131.6
TG tok/s
18277
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 64k | 3,586 | 131.6 | 3.4 GB | current |
| 128k | 2,241 | 95.2 | 4.3 GB | view |