← Back to community benchmarks
Qwen3-14B
Performance
4k
tokens
95.8
PP tok/s
10.2
TG tok/s
42773
TTFT (ms)
9.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 103.0 | 12.9 | 8.0 GB | view |
| 4k | 95.8 | 10.2 | 9.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.9 | 1.00× |
| 2× | 22.7 | 1.76× |
| 4× | 19.7 | 1.53× |