News for hackers. Stuff that matters.
Re:Unsloth Dynamic 3.0 GGUFs by walrus01 on Wednesday August 19, 2026 @06:54PM (#49368210)
It would be nice if unsloth published GGUFs would use a version number or something, because now I have multiple different files on local storage that otherwise have exactly the same name.

"Qwen3.8-27B-UD-Q8_K_XL.gguf" for instance.

The one downloaded at least 4 days ago is a different thing and is NOT the "Dynamic 3.0" GGUF which I am now downloading, which I presume will have a different sha256 checksum?

The unsloth page says dynamic 3.0 is released "today", but I have an older copy of qwen3.8 27B Q8 which I downloaded, if I remember right, at least 4-5 days ago...

https://huggingface.co/unsloth/Qwen3.8-27B-GGUF

Re:Unsloth Dynamic 3.0 GGUFs by prima-facie on Wednesday August 19, 2026 @08:14PM (#49368883)
You can manage these easily with the huggingface python app.

hf download hf://unsloth/Qwen3.8-27B-GGUF \ Qwen3.8-27B-UD-Q4_K_XL.gguf

and then see them with `hf cache ls`.

Prune old versions with `hf cache prune`.

Re:Unsloth Dynamic 3.0 GGUFs by hedora on Wednesday August 19, 2026 @09:52PM (#49369562)
That's terrible. My computer shipped with a filesystem and curl.
Re:Unsloth Dynamic 3.0 GGUFs by mycall on Wednesday August 19, 2026 @10:06PM (#49369625)
There is always SHA256 as the alternative.
Re:Unsloth Dynamic 3.0 GGUFs by cicko on Thursday August 20, 2026 @02:30AM (#49371107)
You can't run models with filesystem and curl.
Re:Unsloth Dynamic 3.0 GGUFs by embedding-shape on Thursday August 20, 2026 @05:29AM (#49372339)
To be fair, you can't run models with "hf download" either...
Re:Unsloth Dynamic 3.0 GGUFs by catchnear4321 on Thursday August 20, 2026 @08:48AM (#49373914)
To be fair, the point was more that cURL isn’t a local hf cache manager, much like it isn’t an inference backend, pointing out that avoiding additional dependencies manages risk at the cost of functionality and/or maintenance overhead…
Re:Unsloth Dynamic 3.0 GGUFs by 14u2c on Wednesday August 19, 2026 @11:18PM (#49369992)
Using git is another option, you'll get the actual commits/history to reference:

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/unsloth/Qwen3.8-27B-GGUF

cd Qwen3.8-27B-GGUF

git lfs pull --include="Qwen3.8-27B-UD-Q8_K_XL.gguf" --exclude=""

Re:Unsloth Dynamic 3.0 GGUFs by prima-facie on Thursday August 20, 2026 @10:05AM (#49374742)
This is very cool, thanks
Re:Unsloth Dynamic 3.0 GGUFs by boredatoms on Thursday August 20, 2026 @10:41AM (#49375296)
Ah this feels much nicer than learning yet another custom vendor cli thing
Re:Unsloth Dynamic 3.0 GGUFs by kristjansson on Thursday August 20, 2026 @11:55AM (#49376381)
hf download maintains each downloaded version in a commit-hash-addressed snapshots dir, with symlinks to the underlying files content-addressed in a blobs dir. It’s not quite git, but it is a stable reference path.
Re:Unsloth Dynamic 3.0 GGUFs by m463 on Wednesday August 19, 2026 @07:48PM (#49368711)
I wonder if there should be some kind of header sort of like a README inside mixed with something like EXIF information that camera images embed.
Re:Unsloth Dynamic 3.0 GGUFs by walrus01 on Wednesday August 19, 2026 @07:49PM (#49368719)
there's metadata in a GGUF (as can be seen when loading one into llama-server with verbose level 4) but it doesn't appear to show what the expected sha256 of the file is.
Re:Unsloth Dynamic 3.0 GGUFs by gunalx on Wednesday August 19, 2026 @08:00PM (#49368789)
Well that would not work as the metadata is also part of the sha, and if you have a sha predictably contain or hash to itself you have a bad hashing algorithm. (Unless of course you mean sha of the weigths and not the gguf itself)
Re:Unsloth Dynamic 3.0 GGUFs by nagaiaida on Wednesday August 19, 2026 @10:11PM (#49369652)
you can just hash the metadata masking out the hash as all zeroes or anything similar to get around that, like header checksums that ostensibly include themselves
Re:Unsloth Dynamic 3.0 GGUFs by close04 on Thursday August 20, 2026 @09:30AM (#49374349)
With large downloads ideally they'd provide all the info upfront. Even some unique code in the name that you can look up in a readme on the site.
Re:Unsloth Dynamic 3.0 GGUFs by jlbprof on Wednesday August 19, 2026 @07:46PM (#49368695)
How can I tell which one I have? I dl'd mine a few days ago.
Re:Unsloth Dynamic 3.0 GGUFs by walrus01 on Wednesday August 19, 2026 @07:49PM (#49368712)
I have just run a sha256 checksum on both copies now, the one I downloaded 4-5 days ago, and the one that's on the unsloth huggingface page released today, and will see if they're the same or different.

(downloaded in the last few hours after the announcement of dynamic 3.0)

Qwen3.8-27B-UD-Q8_K_XL-unsloth-dynamic3.0$ openssl dgst -sha256 *.gguf

SHA2-256(Qwen3.8-27B-UD-Q8_K_XL.gguf)= af36ecb6b5db1407953345b746c14ac93f0657dda413910b4348683a2d990377

=====separator=========

downloaded at least 4 days ago:

Qwen3.8-27B-UD-Q8_K_XL-unsloth-original$ openssl dgst -sha256 Qwen3.8-27B-UD-Q8_K_XL.gguf

SHA2-256(Qwen3.8-27B-UD-Q8_K_XL.gguf)= af36ecb6b5db1407953345b746c14ac93f0657dda413910b4348683a2d990377

So they're actually the same thing, but the announcement says released today... Please let's not confuse the end users any more than they already are.

Re:Unsloth Dynamic 3.0 GGUFs by CMay on Wednesday August 19, 2026 @08:17PM (#49368906)
I think they said they were keeping the old UD 2.0 quant for the larger sizes? So maybe they kept those the same and simply reuploaded them. They said the newer UD 3.0 quant performed worse on some things for the higher quants. So now it's a mix of UD 3.0 and UD 2.0.