← Back to community benchmarks
Qwen3-Coder-Next
Performance
8k
tokens
2,812
PP tok/s
83.8
TG tok/s
2914
TTFT (ms)
43.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,499 | 91.4 | 43.0 GB | view |
| 4k | 2,487 | 87.6 | 43.2 GB | view |
| 8k | 2,812 | 83.8 | 43.4 GB | current |
| 16k | 2,589 | 76.1 | 43.9 GB | view |
| 32k | 2,288 | 51.5 | 44.7 GB | view |
| 64k | 1,614 | 28.7 | 46.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.4 | 1.00× |
| 2× | 156.1 | 1.71× |
| 4× | 247.3 | 2.71× |
| 8× | 325.3 | 3.56× |