← Back to community benchmarks
Qwen3-Coder-Next
Performance
16k
tokens
330.7
PP tok/s
33.8
TG tok/s
49543
TTFT (ms)
45.3
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 296.5 | 42.3 | 43.1 GB | view |
| 4k | 342.9 | 40.8 | 44.0 GB | view |
| 8k | 343.1 | 38.8 | 44.5 GB | view |
| 16k | 330.7 | 33.8 | 45.3 GB | current |
| 32k | 300.2 | 30.9 | 46.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.3 | 1.00× |
| 2× | 55.7 | 1.32× |
| 4× | 72.1 | 1.70× |
| 8× | 86.3 | 2.04× |