← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
382.0
PP tok/s
39.6
TG tok/s
2680
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.10
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 382.0 | 39.6 | 3.3 GB | current |
| 4k | 396.3 | 37.9 | 3.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.6 | 1.00× |
| 2× | 75.8 | 1.91× |
| 4× | 94.6 | 2.39× |