← Back to community benchmarks
Qwen3.5-122B-A10B3.7bit-VL
Performance
4k
tokens
186.7
PP tok/s
21.3
TG tok/s
21939
TTFT (ms)
56.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.21
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 169.8 | 22.9 | 54.5 GB | view |
| 4k | 186.7 | 21.3 | 56.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.9 | 1.00× |
| 2× | 28.4 | 1.24× |
| 4× | 33.8 | 1.48× |