Revision History
Model Compression · 9 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected ALBERT-large's accuracy versus BERT-large, removed a misattributed claim that the SparseGPT paper found 50% sparsity worse than INT4, fixed the Marlin benchmark GPU (H200, not A100) and the NVIDIA pruning example (Qwen3 8B to 6B, not Llama 3.1 8B to 4B), and replaced a reference that did not support the pruning-distillation-quantization ordering claim (plus 15 minor fixes)
Version 9 · Nov 2, 2026, 05:32 PM
- Update: added a video.
Version 8 · Nov 1, 2026, 08:14 AM
- Improve internal links (2026-10-13)
Version 6 · Oct 13, 2026, 10:08 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:05 PM