← Back to community benchmarks
Qwen3-Coder-Next
Performance
16k
tokens
300.4
PP tok/s
31.4
TG tok/s
54538
TTFT (ms)
43.9
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 358.5 | 45.7 | 43.0 GB | view |
| 4k | 348.0 | 43.5 | 43.2 GB | view |
| 8k | 325.3 | 38.6 | 43.4 GB | view |
| 16k | 300.4 | 31.4 | 43.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.7 | 1.00× |
| 2× | 66.2 | 1.45× |
| 4× | 80.2 | 1.75× |