← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
282.9
PP tok/s
28.5
TG tok/s
14477
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 288.7 | 29.1 | 4.0 GB | view |
| 4k | 282.9 | 28.5 | 4.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.1 | 1.00× |
| 2× | 43.2 | 1.48× |
| 4× | 52.0 | 1.79× |