← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
8k
tokens
457.3
PP tok/s
33.1
TG tok/s
17915
TTFT (ms)
81.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.14
macOS
macOS 15.7.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 451.1 | 38.7 | 80.6 GB | view |
| 4k | 473.6 | 37.2 | 80.9 GB | view |
| 8k | 457.3 | 33.1 | 81.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.7 | 1.00× |
| 2× | 57.6 | 1.49× |
| 4× | 61.8 | 1.60× |
| 8× | 73.1 | 1.89× |