← Back to community benchmarks
Qwen3.6-35B-A3BVLM-oQ8
Performance
16k
tokens
844.1
PP tok/s
176.4
TG tok/s
19410
TTFT (ms)
38.6
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
16,384