← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
404.0
PP tok/s
32.7
TG tok/s
2535
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 404.0 | 32.7 | 3.9 GB | current |
| 4k | 400.6 | 29.7 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.7 | 1.00× |
| 2× | 60.7 | 1.86× |
| 4× | 88.7 | 2.71× |