← Back to community benchmarks
Qwen3.5-VLM-122B-A10B-oQ8p
Performance
32k
tokens
764.5
PP tok/s
29.8
TG tok/s
42861
TTFT (ms)
128.1
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
32,768