← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
1k
tokens
319.0
PP tok/s
25.6
TG tok/s
3210
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 319.0 | 25.6 | 4.1 GB | current |
| 4k | 331.7 | 24.8 | 4.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.6 | 1.00× |
| 2× | 48.5 | 1.89× |
| 4× | 66.7 | 2.61× |