inari@piefed.zip to

LocalLLaMA@sh.itjust.worksEnglish · 27 days ago

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses

11

24

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses

inari@piefed.zip to

LocalLLaMA@sh.itjust.worksEnglish · 27 days ago

11

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses - Quesma Blog

I test Unsloth GGUFs of Qwen3.8 27B (Q4_K_M, UD-Q2_K_XL, UD-IQ1_S) with llama.cpp on GPQA Diamond, IFBench, Terminal-Bench 2.1. Q4_K_M matches BF16 abd fits an RTX 4090.

Chat

corvus@lemmy.ml
link
fedilink
English
arrow-up
2·
25 days ago
Someone reported q5_1 having indistinguishable results from q8 for kV cache up to 130k IIRC. You could give it a try.

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

52 users / day
210 users / week
521 users / month
587 users / 6 months
1 local subscriber
5.21K subscribers
69 Posts
309 Comments
Modlog