← Back to community benchmarks
Qwen3-Coder-Next
Performance
8k
tokens
1,290
PP tok/s
70.4
TG tok/s
6350
TTFT (ms)
62.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,110 | 76.6 | 61.6 GB | view |
| 4k | 1,304 | 73.8 | 62.5 GB | view |
| 8k | 1,290 | 70.4 | 62.8 GB | current |
| 16k | 1,211 | 62.5 | 63.5 GB | view |
| 32k | 1,057 | 52.7 | 64.9 GB | view |
| 64k | 830.5 | 36.4 | 67.7 GB | view |
| 128k | 559.6 | 18.9 | 73.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.6 | 1.00× |
| 2× | 111.5 | 1.46× |
| 4× | 150.5 | 1.96× |
| 8× | 192.9 | 2.52× |