← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
424.9
PP tok/s
11.7
TG tok/s
9640
TTFT (ms)
9.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 15.6.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 392.7 | 11.7 | 8.7 GB | view |
| 4k | 424.9 | 11.7 | 9.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.7 | 1.00× |
| 2× | 14.5 | 1.24× |
| 4× | 28.3 | 2.42× |