← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
1k
tokens
365.9
PP tok/s
50.7
TG tok/s
2799
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.8.dev3
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 365.9 | 50.7 | 16.6 GB | current |
| 4k | 372.6 | 40.7 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.7 | 1.00× |
| 4× | 76.0 | 1.50× |