← Back to community benchmarks
Qwen3.5-4B
Performance
8k
tokens
132.1
PP tok/s
16.3
TG tok/s
62033
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 138.6 | 20.5 | 3.9 GB | view |
| 4k | 123.7 | 11.3 | 4.2 GB | view |
| 8k | 132.1 | 16.3 | 4.6 GB | current |
| 16k | 123.7 | 14.4 | 4.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 27.7 | 1.35× |
| 4× | 32.1 | 1.57× |