← Back to community benchmarks
Qwen3-Coder-Next
Performance
16k
tokens
1,460
PP tok/s
59.4
TG tok/s
11219
TTFT (ms)
43.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,318 | 73.0 | 43.0 GB | view |
| 4k | 1,556 | 70.4 | 43.2 GB | view |
| 8k | 1,553 | 67.5 | 43.4 GB | view |
| 16k | 1,460 | 59.4 | 43.9 GB | current |
| 32k | 1,279 | 49.8 | 44.7 GB | view |
| 64k | 1,002 | 37.0 | 46.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.0 | 1.00× |
| 2× | 123.5 | 1.69× |
| 4× | 194.6 | 2.67× |
| 8× | 285.0 | 3.90× |