← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
794.4
PP tok/s
7.8
TG tok/s
1289
TTFT (ms)
12.0
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 794.4 | 7.8 | 12.0 GB | current |
| 4k | 961.8 | 7.7 | 12.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.8 | 1.00× |
| 2× | 11.4 | 1.46× |
| 4× | 21.0 | 2.69× |