← Back to community benchmarks
Qwen3.5-4B
Performance
8k
tokens
392.2
PP tok/s
32.9
TG tok/s
20886
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 399.5 | 37.4 | 3.9 GB | view |
| 4k | 404.2 | 35.5 | 4.2 GB | view |
| 8k | 392.2 | 32.9 | 4.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.4 | 1.00× |
| 2× | 72.5 | 1.94× |
| 4× | 94.1 | 2.52× |
| 8× | 96.8 | 2.59× |