← Back to community benchmarks
Qwen3-32B
Performance
1k
tokens
96.0
PP tok/s
12.0
TG tok/s
10663
TTFT (ms)
18.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 96.0 | 12.0 | 18.0 GB | current |
| 4k | 89.9 | 11.0 | 18.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.0 | 1.00× |
| 2× | 22.1 | 1.84× |
| 4× | 24.4 | 2.03× |