← Back to community benchmarks
Qwen3-4B-Thinking-2507
Performance
1k
tokens
258.6
PP tok/s
33.5
TG tok/s
3961
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.8
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 258.6 | 33.5 | 4.7 GB | current |
| 4k | 258.1 | 28.1 | 5.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.5 | 1.00× |
| 2× | 53.5 | 1.60× |
| 4× | 60.3 | 1.80× |