← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
507.7
PP tok/s
91.2
TG tok/s
2017
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 507.7 | 91.2 | 3.4 GB | current |
| 4k | 561.8 | 84.2 | 4.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.2 | 1.00× |
| 2× | 110.7 | 1.21× |
| 4× | 123.9 | 1.36× |