← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
442.4
PP tok/s
47.7
TG tok/s
18518
TTFT (ms)
67.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 528.8 | 54.4 | 66.3 GB | view |
| 4k | 497.0 | 51.7 | 66.7 GB | view |
| 8k | 442.4 | 47.7 | 67.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.4 | 1.00× |
| 2× | 77.7 | 1.43× |
| 4× | 90.1 | 1.66× |
| 8× | 111.4 | 2.05× |