Thiago de Arruda Padilha
tarruda
AI & ML interests
None yet
Recent Activity
new activity 4 days ago
bartowski/prefeitura-rio_Rio-3.5-Open-397B-GGUF:Final model? updated a model 5 days ago
tarruda/Rio-3.5-Open-397B-GGUF published a model 6 days ago
tarruda/Rio-3.5-Open-397B-GGUFOrganizations
None yet
Final model?
👍 1
7
#1 opened 9 days ago
by
blankreg
Aren't the thinking traces hidden in the OpenAI API?
1
#2 opened 6 days ago
by
tarruda
Model Looping in Reasoning
2
#12 opened 8 days ago
by
remichu
Despite the way the project was released, this is a good model.
👍 5
9
#25 opened 7 days ago
by
tarruda
Gguf
👍 5
5
#1 opened 10 days ago
by
cdani
Some practical tips for using Step 3.7 GGUFs
🧠👍 2
5
#6 opened 23 days ago
by
tarruda
PPQ(Q)/PPL(base) and KLD seems significantly worse than Step 3.5 Flash
👀 1
22
#2 opened 23 days ago
by
tarruda
Supers Found in model
❤️ 2
9
#11 opened 22 days ago
by
tcclaviger
Tool calling bug in the official API
👍 1
#12 opened 21 days ago
by
tarruda
imatrix corpus
3
#3 opened 25 days ago
by
ghit72
MTP support merged in llama.cpp
13
#10 opened about 1 month ago
by
tarruda
MTP Support
👍 2
9
#13 opened about 1 month ago
by
anikifoss
Suggestion: Add IQ3 variants.
👍 2
4
#7 opened about 1 month ago
by
tarruda
Any llama.cpp parameters to work around the looping?
👍 1
2
#12 opened about 1 month ago
by
tarruda
Can you share the command you used to create the BF16 ggus?
2
#10 opened about 2 months ago
by
tarruda
IQ3_S doesn't load with "wrong number of tensors"
2
#9 opened about 2 months ago
by
tarruda
New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF about 2 months ago
Can the MTP version currently be loaded in LM Studio?
❤️👍 3
5
#2 opened about 2 months ago
by
cclongdevil
Excellent work on this one
4
#8 opened about 2 months ago
by
tarruda
Keep the mtp layer weight
👍 2
10
#5 opened about 2 months ago
by
Light4Bear
Seems like chat template is broken?
4
#3 opened about 2 months ago
by
tarruda