← Back to community benchmarks
Qwen3.5-122B-A10B-oQ4-mtp
Performance
1k
tokens
979.5
PP tok/s
56.5
TG tok/s
1045
TTFT (ms)
68.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 979.5 | 56.5 | 68.6 GB | current |
| 4k | 1,447 | 54.1 | 70.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.5 | 1.00× |
| 2× | 78.2 | 1.38× |
| 4× | 105.2 | 1.86× |