← Back to community benchmarks
Qwopus3.6-27B-v2-oQ6-fp16-mtp
Performance
4k
tokens
113.6
PP tok/s
11.5
TG tok/s
36071
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.1
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 129.4 | 10.5 | 23.0 GB | view |
| 4k | 113.6 | 11.5 | 24.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.5 | 1.00× |
| 2× | 15.4 | 1.47× |