← Back to community benchmarks
Qwen3-Coder-Next
Performance
4k
tokens
1,470
PP tok/s
61.4
TG tok/s
2786
TTFT (ms)
80.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 15.6.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,089 | 63.5 | 80.1 GB | view |
| 4k | 1,470 | 61.4 | 80.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.5 | 1.00× |
| 2× | 110.0 | 1.73× |
| 4× | 171.3 | 2.70× |