← Back to community benchmarks
Qwen3-Coder-Next
Performance
16k
tokens
1,059
PP tok/s
48.3
TG tok/s
15475
TTFT (ms)
80.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 902.1 | 60.6 | 80.1 GB | view |
| 4k | 1,193 | 59.7 | 80.3 GB | view |
| 8k | 1,176 | 57.2 | 80.5 GB | view |
| 16k | 1,059 | 48.3 | 80.9 GB | current |
| 32k | 897.7 | 42.6 | 81.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.6 | 1.00× |
| 2× | 101.3 | 1.67× |
| 4× | 147.5 | 2.43× |