← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
144.9
PP tok/s
22.3
TG tok/s
7065
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 144.9 | 22.3 | 3.9 GB | current |
| 4k | 144.3 | 20.8 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.3 | 1.00× |
| 2× | 33.1 | 1.48× |
| 4× | 34.1 | 1.53× |
| 8× | 29.6 | 1.33× |