← Back to community benchmarks
Qwen3-Coder-Next
Performance
8k
tokens
427.1
PP tok/s
46.1
TG tok/s
19182
TTFT (ms)
62.0
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 464.3 | 53.4 | 61.6 GB | view |
| 4k | 443.4 | 50.2 | 61.7 GB | view |
| 8k | 427.1 | 46.1 | 62.0 GB | current |
| 16k | 412.9 | 38.1 | 62.4 GB | view |
| 32k | 379.4 | 25.5 | 63.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.4 | 1.00× |
| 2× | 65.1 | 1.22× |
| 4× | 78.2 | 1.46× |
| 8× | 97.9 | 1.83× |