← Back to community benchmarks
Qwen3-Coder-Next
Performance
4k
tokens
434.8
PP tok/s
55.0
TG tok/s
9420
TTFT (ms)
43.2
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 467.5 | 57.8 | 43.0 GB | view |
| 4k | 434.8 | 55.0 | 43.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.8 | 1.00× |
| 2× | 82.0 | 1.42× |
| 4× | 96.8 | 1.67× |