← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
1k
tokens
411.8
PP tok/s
55.2
TG tok/s
2487
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 411.8 | 55.2 | 16.6 GB | current |
| 4k | 442.6 | 46.1 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.2 | 1.00× |
| 2× | 77.1 | 1.40× |
| 4× | 90.8 | 1.64× |