← Back to community benchmarks
Qwen3.5-4B
Performance
8k
tokens
321.8
PP tok/s
27.9
TG tok/s
25458
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 354.4 | 35.3 | 3.9 GB | view |
| 4k | 347.2 | 32.5 | 4.2 GB | view |
| 8k | 321.8 | 27.9 | 4.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.3 | 1.00× |
| 2× | 54.3 | 1.54× |
| 4× | 51.0 | 1.44× |
| 8× | 55.2 | 1.56× |