← Back to community benchmarks
Qwen3.6-35B-A3BVLM-oQ8
Performance
1k
tokens
1,516
PP tok/s
267.8
TG tok/s
675
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
64 GB
GPU Cores
64
Software
oMLX
v0.3.8.dev1
macOS
macOS 26.4.1
Context
1,024