← Back to community benchmarks
Qwen3-4B-Thinking-2507
Performance
1k
tokens
388.6
PP tok/s
38.8
TG tok/s
2635
TTFT (ms)
2.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.10
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 388.6 | 38.8 | 2.8 GB | current |
| 4k | 354.1 | 31.7 | 3.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.8 | 1.00× |
| 2× | 69.7 | 1.80× |
| 4× | 88.0 | 2.27× |
| 8× | 90.5 | 2.33× |