← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
1,600
PP tok/s
22.8
TG tok/s
640
TTFT (ms)
3.5
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,600 | 22.8 | 3.5 GB | current |
| 4k | 2,048 | 22.8 | 3.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.8 | 1.00× |
| 2× | 36.5 | 1.60× |
| 4× | 72.7 | 3.19× |