← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
1,320
PP tok/s
104.8
TG tok/s
3103
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,287 | 112.7 | 4.0 GB | view |
| 4k | 1,320 | 104.8 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 112.7 | 1.00× |
| 2× | 200.7 | 1.78× |
| 4× | 241.2 | 2.14× |
| 8× | 257.8 | 2.29× |