← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
394.8
PP tok/s
36.8
TG tok/s
10374
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 401.5 | 38.5 | 3.9 GB | view |
| 4k | 394.8 | 36.8 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.5 | 1.00× |
| 2× | 72.9 | 1.89× |
| 4× | 92.9 | 2.41× |