← Back to community benchmarks
Qwen3-Coder-NextQ9
Performance
1k
tokens
1,362
PP tok/s
63.5
TG tok/s
752
TTFT (ms)
84.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,362 | 63.5 | 84.8 GB | current |
| 4k | 1,972 | 62.4 | 85.7 GB | view |
| 64k | 1,288 | 50.4 | 90.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.5 | 1.00× |
| 2× | 100.0 | 1.57× |
| 4× | 157.9 | 2.49× |
| 8× | 231.9 | 3.65× |