← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
441.1
PP tok/s
67.8
TG tok/s
9286
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
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 | 434.6 | 72.8 | 4.0 GB | view |
| 4k | 441.1 | 67.8 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 72.8 | 1.00× |
| 2× | 86.1 | 1.18× |
| 4× | 93.6 | 1.29× |
| 8× | 76.3 | 1.05× |