← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
1,835
PP tok/s
66.3
TG tok/s
558
TTFT (ms)
61.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,835 | 66.3 | 61.6 GB | current |
| 4k | 2,704 | 64.2 | 62.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.3 | 1.00× |
| 2× | 94.5 | 1.43× |
| 4× | 142.0 | 2.14× |