← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
823.8
PP tok/s
6.3
TG tok/s
4972
TTFT (ms)
12.1
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.2.11
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 652.0 | 6.4 | 12.0 GB | view |
| 4k | 823.8 | 6.3 | 12.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.4 | 1.00× |
| 2× | 10.5 | 1.64× |
| 4× | 20.7 | 3.23× |