← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
401.1
PP tok/s
37.7
TG tok/s
2553
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 401.1 | 37.7 | 3.9 GB | current |
| 4k | 400.5 | 35.4 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.7 | 1.00× |
| 2× | 72.6 | 1.93× |
| 4× | 92.6 | 2.46× |
| 8× | 94.9 | 2.52× |