← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
962.3
PP tok/s
68.5
TG tok/s
1064
TTFT (ms)
43.0
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 962.3 | 68.5 | 43.0 GB | current |
| 4k | 1,096 | 64.8 | 43.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.5 | 1.00× |
| 2× | 116.5 | 1.70× |
| 4× | 167.1 | 2.44× |