← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
199.0
PP tok/s
32.1
TG tok/s
5145
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 15.0.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 199.0 | 32.1 | 3.9 GB | current |
| 4k | 198.3 | 30.4 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.1 | 1.00× |
| 2× | 45.3 | 1.41× |
| 4× | 47.5 | 1.48× |
| 8× | 39.7 | 1.24× |