← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
203.2
PP tok/s
1.9
TG tok/s
5039
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 203.2 | 1.9 | 11.7 GB | current |
| 4k | 240.3 | 1.9 | 11.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 1.9 | 1.00× |
| 2× | 3.7 | 1.95× |
| 4× | 7.5 | 3.95× |