← Back to community benchmarks
OpenYourMind--Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-MTPLX
Performance
1k
tokens
1,052
PP tok/s
68.1
TG tok/s
973
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.3
macOS
macOS 27.0
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,052 | 68.1 | 65.6 GB | current |
| 4k | 1,486 | 65.5 | 66.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.1 | 1.00× |
| 2× | 100.5 | 1.48× |
| 4× | 101.7 | 1.49× |