← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
366.9
PP tok/s
38.8
TG tok/s
11165
TTFT (ms)
66.9
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 299.6 | 40.8 | 65.6 GB | view |
| 4k | 366.9 | 38.8 | 66.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.8 | 1.00× |
| 2× | 58.9 | 1.44× |
| 4× | 78.6 | 1.93× |
| 8× | 97.7 | 2.39× |