Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Layer Pruning Efficiency Evaluation on LLaVA-NeXT 8B
Loading...
18.1
Peak VRAM (GB)
TopoVLM
17.552
21.251
24.95
28.649
Apr 14, 2026
Peak VRAM (GB)
Search Time (min)
Calibration Passes
Inference Latency (ms)
Speedup
Updated 3mo ago
Evaluation Results
Method
Method
Links
Peak VRAM (GB)
Search Time (min)
Calibration Passes
Inference Latency (ms)
Speedup
TopoVLM
Sparsity=50%
2026.04
18.1
5.7
1
60.3
1.75
TAMP
Sparsity=50%
2026.04
18.3
16.8
5
63.4
1.66
Wanda
Sparsity=50%
2026.04
18.5
18.9
6
64.9
1.62
SparseGPT
Sparsity=50%
2026.04
18.7
22.3
8
65.8
1.6
LLM-Pruner
Sparsity=50%
2026.04
19.2
14.6
5
67.1
1.57
Full Model
Sparsity=0%
2026.04
31.8
-
-
105.4
1
LaCo
Sparsity=50%
2026.04
-
17.4
5
-
-
Feedback
Search any
task
Search any
task