← Back to community benchmarks

Qwen3.5-VL-27B-8bitCRACK

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-10
Performance
4k
tokens
421.8
PP tok/s
21.0
TG tok/s
9712
TTFT (ms)
29.5
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.7
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 412.3 21.5 29.1 GB view
4k 421.8 21.0 29.5 GB current
64k 333.1 13.5 36.2 GB view
Batching Results
Batch Size TG tok/s Speedup
21.5 1.00×
38.5 1.79×
57.6 2.68×
114.7 5.33×