← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
199.5
PP tok/s
28.9
TG tok/s
20527
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
8 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 196.0 | 30.3 | 3.9 GB | view |
| 4k | 199.5 | 28.9 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.3 | 1.00× |
| 2× | 44.5 | 1.47× |
| 4× | 46.2 | 1.52× |