← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
1,227
PP tok/s
64.5
TG tok/s
835
TTFT (ms)
43.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 15.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,227 | 64.5 | 43.1 GB | current |
| 4k | 1,354 | 64.8 | 43.8 GB | view |
| 64k | 746.4 | 52.1 | 45.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.5 | 1.00× |
| 2× | 118.2 | 1.83× |
| 4× | 183.4 | 2.84× |
| 8× | 270.7 | 4.20× |