← Back to community benchmarks
Qwopus3.6-27B-v2-oQ4-fp16-mtp
Performance
8k
tokens
198.2
PP tok/s
20.7
TG tok/s
41336
TTFT (ms)
18.5
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.4.4
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 206.2 | 22.1 | 16.4 GB | view |
| 4k | 210.7 | 21.4 | 17.9 GB | view |
| 8k | 198.2 | 20.7 | 18.5 GB | current |
| 16k | 201.7 | 19.9 | 19.8 GB | view |
| 32k | 187.5 | 18.8 | 22.3 GB | view |
| 64k | 162.5 | 16.3 | 27.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.1 | 1.00× |
| 2× | 43.5 | 1.97× |
| 4× | 88.3 | 4.00× |
| 8× | 176.6 | 7.99× |