← Back to community benchmarks
Qwen3.5-VLM-122B-A10B-oQ8p
Performance
16k
tokens
872.7
PP tok/s
35.3
TG tok/s
18773
TTFT (ms)
125.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
256 GB
GPU Cores
80
Software
oMLX
v0.3.0
macOS
macOS 26.3.1
Context
16,384