← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
405.7
PP tok/s
39.1
TG tok/s
2524
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 405.7 | 39.1 | 6.7 GB | current |
| 4k | 404.0 | 36.6 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.1 | 1.00× |
| 2× | 73.7 | 1.88× |
| 4× | 95.0 | 2.43× |