← Back to community benchmarks
Qwen3.5-122B-A10B-oQ3
Performance
16k
tokens
163.5
PP tok/s
27.8
TG tok/s
100205
TTFT (ms)
50.6
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.2rc1
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 177.5 | 32.2 | 47.9 GB | view |
| 16k | 163.5 | 27.8 | 50.6 GB | current |
| 64k | 104.2 | 19.8 | 52.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.2 | 1.00× |
| 2× | 38.5 | 1.20× |
| 4× | 76.8 | 2.39× |