← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
142.9
PP tok/s
21.3
TG tok/s
7164
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 142.9 | 21.3 | 3.9 GB | current |
| 4k | 140.4 | 20.1 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.3 | 1.00× |
| 2× | 32.4 | 1.52× |
| 4× | 34.0 | 1.60× |
| 8× | 27.8 | 1.31× |