← Back to community benchmarks
Qwen3-Coder-Next
Performance
4k
tokens
689.8
PP tok/s
59.3
TG tok/s
5938
TTFT (ms)
44.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.5
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 575.0 | 61.8 | 43.1 GB | view |
| 4k | 689.8 | 59.3 | 44.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.8 | 1.00× |
| 2× | 88.2 | 1.43× |
| 4× | 117.7 | 1.90× |