← Back to community benchmarks
qwen35-9bturboquant-tq3
Performance
4k
tokens
223.0
PP tok/s
19.7
TG tok/s
18364
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 216.3 | 20.8 | 5.7 GB | view |
| 4k | 223.0 | 19.7 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.8 | 1.00× |
| 2× | 40.6 | 1.95× |
| 4× | 52.2 | 2.51× |