← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
196.2
PP tok/s
30.1
TG tok/s
20872
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 191.6 | 31.3 | 3.3 GB | view |
| 4k | 196.2 | 30.1 | 3.9 GB | current |
| 8k | 193.6 | 28.0 | 4.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.3 | 1.00× |
| 2× | 44.5 | 1.42× |
| 4× | 46.4 | 1.48× |
| 8× | 39.8 | 1.27× |