← Back to community benchmarks
Qwopus3.6-27B-v2-oQ4-fp16-mtp
Performance
1k
tokens
325.3
PP tok/s
44.0
TG tok/s
3148
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.4.0rc2
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 325.3 | 44.0 | 16.7 GB | current |
| 4k | 344.4 | 42.4 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.0 | 1.00× |
| 2× | 86.0 | 1.95× |
| 4× | 168.7 | 3.83× |