← Back to community benchmarks
Qwen3-Coder-Next
Performance
4k
tokens
1,919
PP tok/s
68.4
TG tok/s
2134
TTFT (ms)
43.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.11
macOS
macOS 15.3.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,561 | 71.7 | 43.0 GB | view |
| 4k | 1,919 | 68.4 | 43.2 GB | current |
| 8k | 1,929 | 65.0 | 43.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.7 | 1.00× |
| 2× | 125.0 | 1.74× |