← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
1k
tokens
1,194
PP tok/s
78.2
TG tok/s
858
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,194 | 78.2 | 23.7 GB | current |
| 4k | 1,285 | 64.6 | 24.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 78.2 | 1.00× |
| 2× | 113.1 | 1.45× |
| 4× | 142.9 | 1.83× |