← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
396.2
PP tok/s
34.2
TG tok/s
10337
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.0.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 397.8 | 37.1 | 3.9 GB | view |
| 4k | 396.2 | 34.2 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.1 | 1.00× |
| 2× | 70.9 | 1.91× |
| 4× | 71.1 | 1.92× |