← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
1,049
PP tok/s
35.3
TG tok/s
976
TTFT (ms)
82.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,049 | 35.3 | 82.8 GB | current |
| 4k | 1,321 | 65.6 | 81.0 GB | view |
| 8k | 1,309 | 63.0 | 81.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.3 | 1.00× |
| 2× | 105.9 | 3.00× |