← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct-4bit-dwq-v2
Performance
4k
tokens
879.2
PP tok/s
61.7
TG tok/s
4659
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 953.3 | 71.9 | 16.6 GB | view |
| 4k | 879.2 | 61.7 | 17.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.9 | 1.00× |
| 2× | 111.2 | 1.55× |
| 4× | 144.5 | 2.01× |
| 8× | 177.2 | 2.46× |