← Back to community benchmarks
Qwopus3___5-27B-v3___5
Performance
4k
tokens
339.5
PP tok/s
11.8
TG tok/s
12064
TTFT (ms)
53.2
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 293.2 | 12.1 | 51.7 GB | view |
| 4k | 339.5 | 11.8 | 53.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.1 | 1.00× |
| 2× | 9.9 | 0.82× |
| 4× | 19.7 | 1.63× |