← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
260.1
PP tok/s
2.3
TG tok/s
15746
TTFT (ms)
11.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 15.7.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 225.7 | 2.3 | 11.7 GB | view |
| 4k | 260.1 | 2.3 | 11.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 2.3 | 1.00× |
| 2× | 4.4 | 1.91× |
| 4× | 8.7 | 3.78× |