← Back to community benchmarks
Qwen3.5-4B
Performance
32k
tokens
281.4
PP tok/s
31.0
TG tok/s
116454
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 323.2 | 59.8 | 4.0 GB | view |
| 4k | 319.7 | 54.8 | 4.2 GB | view |
| 8k | 312.2 | 49.6 | 4.6 GB | view |
| 16k | 302.8 | 40.7 | 5.3 GB | view |
| 32k | 281.4 | 31.0 | 6.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.8 | 1.00× |
| 2× | 68.7 | 1.15× |
| 4× | 73.1 | 1.22× |
| 8× | 63.8 | 1.07× |