← Back to community benchmarks
Qwen3-4B-Instruct-2507
Performance
4k
tokens
356.0
PP tok/s
30.0
TG tok/s
11507
TTFT (ms)
3.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.6
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 388.1 | 37.5 | 2.8 GB | view |
| 4k | 356.0 | 30.0 | 3.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.5 | 1.00× |
| 2× | 69.3 | 1.85× |
| 4× | 88.9 | 2.37× |