← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
373.2
PP tok/s
54.3
TG tok/s
10975
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 369.8 | 59.1 | 4.0 GB | view |
| 4k | 373.2 | 54.3 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.1 | 1.00× |
| 2× | 78.8 | 1.33× |
| 4× | 84.6 | 1.43× |