← Back to community benchmarks
Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-MTPLX
Performance
8k
tokens
1,395
PP tok/s
46.0
TG tok/s
5872
TTFT (ms)
67.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.1
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 905.2 | 50.8 | 65.6 GB | view |
| 4k | 1,418 | 49.1 | 66.9 GB | view |
| 8k | 1,395 | 46.0 | 67.8 GB | current |
| 16k | 1,280 | 45.4 | 69.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.8 | 1.00× |
| 2× | 75.2 | 1.48× |
| 4× | 112.0 | 2.20× |