PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
PrismQuant's INT4 rotations nearly match full precision on Llama-3.1-70B and speed Llama-3.1-8B inference.
58
AI model
Llama-3.1-70B
- Mentions · 7d0
- Mentions · 30d0
- All mentions1
- First seenSep 25, 2026
- Last mentionedSep 25, 2026
Timeline
1 articles · newest firstAppears with
- PrismQuantproduct · 1
- Mistral AIvendor · 1
- Alibabavendor · 1
- Llama-3.2-3Bai model · 1
- Llama-3.1-8Bai model · 1
- Metavendor · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.