tib nak
Tibbnak
AI & ML interests
None yet
Recent Activity
liked a model 2 days ago
26B-Suite/Plainspeak-Dial-Gemma-4-26B-A4B-BakeVector liked a model 2 days ago
mradermacher/Qwen3.8-27B-heretic-ara-i1-GGUF liked a model 3 days ago
mradermacher/Nemotron-3.5-30B-A3B-Antislop-FTPO-i1-GGUFOrganizations
None yet
https://huggingface.co/thoughtworks/Nemotron-3.5-30B-A3B-Antislop-FTPO
➕ 1
1
#2788 opened 5 days ago
by
Tibbnak
New activity in llmfan46/LongCat-Flash-Lite-Uncensored-Heretic-Native-MTP-Preserved-GGUF 17 days ago
How did you even quant this and what did you use?
8
#1 opened 17 days ago
by
Tibbnak
🪞 Arbitrary Rank Inversion (ARI)
👍 1
6
#1 opened about 2 months ago
by
Naphula
Good!
🤗👀 1
13
#1 opened 2 months ago
by
usermma
A questionable choice for testing...
5
#1 opened 2 months ago
by
pix2pix
token_embd.weight and *.attn_output.weight need to be q8_0 or higher for gemma 4 models
6
#1 opened 2 months ago
by
Tibbnak
https://huggingface.co/Gryphe/Pantheon-Reasoning-26B-A4B-1.1
1
#2521 opened 2 months ago
by
Tibbnak
iq3_xs spits out gibberish
🔥 2
10
#2 opened 3 months ago
by
Hansdudin202
how long do you take to approve?
1
#1 opened 9 months ago
by
jo987654321
Hurry! 🐌
17
#1 opened 3 months ago
by
McG-221
There's got to be a better way.
23
#6 opened 5 months ago
by
phil111
brayniac/Qwen3.5-35B-A3B-heretic
1
#1911 opened 6 months ago
by
Tibbnak
Restart the the gguf-my-repo to update the version of llama cpp?
#5 opened 6 months ago
by
Tibbnak
Higher pplx on your quants than I'd expect
1
#1 opened 7 months ago
by
Tibbnak
Thinking?
4
#1 opened 11 months ago
by
owao
What sampler settings have you had sucess with?
#1 opened about 1 year ago
by
Tibbnak
Can you support the 128k claims?
1
#1 opened about 1 year ago
by
Tibbnak
Exl3 might be SOTA?
1
#1 opened about 1 year ago
by
Tibbnak
What is the significance of the data in the model card?
12
#1 opened over 1 year ago
by
Tibbnak
General impression
5
#1 opened almost 2 years ago
by
Diavator