← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
3,371
PP tok/s
212.7
TG tok/s
304
TTFT (ms)
2.0
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,371 | 212.7 | 2.0 GB | current |
| 4k | 3,391 | 199.5 | 2.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 212.7 | 1.00× |
| 2× | 295.2 | 1.39× |
| 4× | 333.6 | 1.57× |
| 8× | 462.7 | 2.18× |