← Back to community benchmarks
Qwen3.5-4B
Performance
16k
tokens
339.8
PP tok/s
28.6
TG tok/s
48222
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.6
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 381.3 | 37.8 | 3.9 GB | view |
| 16k | 339.8 | 28.6 | 4.8 GB | current |
| 64k | 236.1 | 14.2 | 8.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.8 | 1.00× |
| 2× | 70.2 | 1.86× |
| 4× | 84.8 | 2.24× |
| 8× | 83.0 | 2.20× |