← Back to community benchmarks
Qwen3.6-35B-A3BVLM-oQ8
Performance
1k
tokens
1,084
PP tok/s
193.4
TG tok/s
944
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
64 GB
GPU Cores
64
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024