← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
1,216
PP tok/s
130.6
TG tok/s
842
TTFT (ms)
2.0
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.2.12
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,216 | 130.6 | 2.0 GB | current |
| 4k | 1,391 | 123.7 | 2.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 130.6 | 1.00× |
| 2× | 227.0 | 1.74× |
| 4× | 276.7 | 2.12× |