← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
260.6
PP tok/s
20.5
TG tok/s
3929
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 260.6 | 20.5 | 3.9 GB | current |
| 4k | 265.6 | 19.2 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 34.0 | 1.66× |
| 4× | 89.9 | 4.39× |