← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
1,230
PP tok/s
72.3
TG tok/s
832
TTFT (ms)
43.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.20.dev1
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,230 | 72.3 | 43.1 GB | current |
| 4k | 1,504 | 69.2 | 44.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 72.3 | 1.00× |
| 2× | 113.1 | 1.56× |
| 4× | 155.1 | 2.15× |