← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
396.8
PP tok/s
36.6
TG tok/s
10322
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 381.6 | 38.7 | 3.3 GB | view |
| 4k | 396.8 | 36.6 | 3.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.7 | 1.00× |
| 2× | 73.3 | 1.89× |
| 4× | 90.4 | 2.34× |