← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
424.7
PP tok/s
44.2
TG tok/s
9643
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 423.7 | 47.6 | 3.9 GB | view |
| 4k | 424.7 | 44.2 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.6 | 1.00× |
| 2× | 95.5 | 2.01× |
| 4× | 127.1 | 2.67× |