← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
431.1
PP tok/s
48.7
TG tok/s
2375
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 431.1 | 48.7 | 3.9 GB | current |
| 4k | 431.4 | 46.0 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.7 | 1.00× |
| 2× | 96.0 | 1.97× |
| 4× | 132.6 | 2.72× |