Sam McLeod personal blog
Bringing K/V context quantisation to Ollama
K/V context cache quantisation has been added to Ollama. This enables significant reductions in VRAM usage, allowing users to realise the potential of expanded context sizes and run larger models at their existing context sizes.
- Points
- 220
- HN comments
- 32
- Submissions
- 1
- Cited by
- 4 commenters
AI & Machine LearningSoftware Engineering2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Dec 5, 2024 | Bringing K/V context quantisation to Ollama by mchiang | 220 | 32 |
Cited in comments
Linked from 4 Hacker News comments by 4 different people, from Dec 2024 to Mar 2026.
Most recent:
- 0xbadcafebee · Mar 2, 2026
- wkat4242 · Feb 12, 2025
- jmorgan · Jan 26, 2025
- smcleod · Dec 6, 2024
