← Back to community benchmarks
Qwen3-4B-Instruct-2507
Performance
1k
tokens
219.7
PP tok/s
34.6
TG tok/s
4661
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.2.9
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 219.7 | 34.6 | 3.8 GB | current |
| 4k | 205.8 | 29.8 | 4.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.6 | 1.00× |
| 2× | 38.6 | 1.12× |
| 4× | 41.0 | 1.18× |