← Back to community benchmarks
Qwen3-Coder-Next
Performance
1k
tokens
292.6
PP tok/s
41.1
TG tok/s
3500
TTFT (ms)
33.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 292.6 | 41.1 | 33.8 GB | current |
| 4k | 318.2 | 38.5 | 33.9 GB | view |
| 8k | 293.8 | 35.6 | 34.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.1 | 1.00× |
| 2× | 54.8 | 1.33× |
| 4× | 60.0 | 1.46× |
| 8× | 61.6 | 1.50× |