← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
282.6
PP tok/s
3.1
TG tok/s
3623
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
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 | 282.6 | 3.1 | 11.7 GB | current |
| 4k | 321.3 | 3.1 | 11.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 3.1 | 1.00× |
| 2× | 5.6 | 1.81× |
| 4× | 10.9 | 3.52× |