← Back to community benchmarks

llava-v1.6-34b

M3 Max (30c) · 96 GB · 8bit · 2026-03-15
Performance
8k
tokens
100.5
PP tok/s
6.8
TG tok/s
81626
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.2.12
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 126.8 7.4 35.1 GB view
4k 104.6 7.3 36.0 GB view
8k 100.5 6.8 37.0 GB current
Batching Results
Batch Size TG tok/s Speedup
7.4 1.00×
11.3 1.53×
11.7 1.58×