← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
467.5
PP tok/s
57.8
TG tok/s
2190
TTFT (ms)
43.0
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 467.5 | 57.8 | 43.0 GB | current |
| 4k | 434.8 | 55.0 | 43.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.8 | 1.00× |
| 2× | 82.0 | 1.42× |
| 4× | 96.8 | 1.67× |