corpus.blog
41554 blogs · 4,504,310 posts Claim your blog
Record · corpus.blog/posts/01a087a0-cbef-7344-bfc4-f0657e8f2b82

Expert-aware quantisation: near-Q4 quality at near-Q2 size?

Martin Alderson · published 22 June 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at martinalderson.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
12
Words captured
1,512

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
A brief history of KV cache compression developments Read at the source ↗
martinalderson.com
A little tool to visualise MoE expert routing Read at the source ↗
martinalderson.com
https://arxiv.org/abs/2511.15015
arxiv.org
https://arxiv.org/abs/2410.06270
arxiv.org
https://arxiv.org/abs/2509.02512
arxiv.org
https://arxiv.org/abs/2306.00978
arxiv.org
https://arxiv.org/abs/2210.17323
arxiv.org
https://arxiv.org/abs/2211.10438
arxiv.org
https://arxiv.org/abs/2306.03078
arxiv.org
https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md
github.com
https://machinelearning.apple.com/research/introducing-apple-foundation-models
machinelearning.apple.com
https://martinalderson.com/contact/
martinalderson.com