← Back to community benchmarks
Qwen3.5-122B-A10B-heretic-v2-2.34bit-msq
Performance
4k
tokens
466.8
PP tok/s
43.4
TG tok/s
8775
TTFT (ms)
42.8
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
128 GB
GPU Cores
76
Software
oMLX
v0.3.6
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 360.5 | 45.6 | 41.5 GB | view |
| 4k | 466.8 | 43.4 | 42.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.6 | 1.00× |
| 2× | 75.9 | 1.66× |
| 4× | 100.2 | 2.20× |