← Back to community benchmarks
Qwen3.5-122B-A10B3.7bit-VL-v2
Performance
4k
tokens
225.0
PP tok/s
31.7
TG tok/s
18204
TTFT (ms)
55.6
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.3.4
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 196.9 | 33.8 | 54.3 GB | view |
| 4k | 225.0 | 31.7 | 55.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.8 | 1.00× |
| 2× | 46.4 | 1.37× |
| 4× | 92.3 | 2.73× |