← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
406.1
PP tok/s
37.3
TG tok/s
2522
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 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 | 406.1 | 37.3 | 3.9 GB | current |
| 4k | 403.5 | 35.4 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.3 | 1.00× |
| 2× | 70.8 | 1.90× |
| 4× | 95.4 | 2.56× |