Thiago de Arruda Padilha

tarruda's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in AesSedai/Qwen3.8-Flash-Next-GGUF 22 days ago

Keep ngram tensors unquantized

15

#2 opened 28 days ago by

Mushoz

New activity in bartowski/DeepSeek-V4-Flash-GGUF 25 days ago

DeepSeek-V4-Flash-0731

11

#6 opened about 2 months ago by

eleius

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 26 days ago

Share your model speed here

🤝 11

31

#3 opened about 1 month ago by

anvme

New activity in nex-agi/Nex-N2-mini 29 days ago

Very good model, punches above its weight.

➕ 1

3

#13 opened 2 months ago by

tarruda

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 1 month ago

i wanted to test the new unsloth studio for this model but it hangs all the time

4

#13 opened about 1 month ago by

Manni1000

how IQ1_S is 72Gb :\

12

#5 opened about 1 month ago by

Darkknight535

New activity in ddalcu/MiniMax-H3-FL2VA-MLX-Serve-8bit about 2 months ago

Any documentation on how to run this?

3

#1 opened about 2 months ago by

tarruda

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 about 2 months ago

Reasoning loops

➕ 4

22

#39 opened about 2 months ago by

d3lavar

New activity in tarruda/DeepSeek-V4-Flash-GGUF about 2 months ago

Quants for updated version?

12

#2 opened about 2 months ago by

LagOps

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 about 2 months ago

multimodal

🔥👍 6

8

#13 opened about 2 months ago by

MaziyarPanahi

Is dspark already included in these weights?

6

#6 opened about 2 months ago by

tarruda

New activity in tarruda/Nex-N2-Pro-GGUF about 2 months ago

Are you actively using this?

2

#1 opened about 2 months ago by

qenme

New activity in tarruda/Step-3.7-Flash-GGUF 2 months ago

Reasoning Budget Message=?

2

#1 opened 2 months ago by

BingoBird

New activity in ornith-ai/Ornith-1.0-397B 2 months ago

120b class?

👍➕ 10

6

#11 opened 3 months ago by

WyattTheSkid

New activity in nex-agi/Nex-N2-Pro 2 months ago

What a Monster. It is very good...

🔥 3

23

#5 opened 4 months ago by

Hunterx

New activity in stepfun-ai/Step-3.7-Flash 3 months ago

Can we add something like Qwen's preserve_thinking to the chat template?

1

#15 opened 3 months ago by

tarruda

New activity in tarruda/DeepSeek-V4-Flash-GGUF 3 months ago

Missing tensors?

5

#1 opened 3 months ago by

Mushoz

New activity in bartowski/DeepSeek-V4-Flash-GGUF 3 months ago

Gen rubbish when set -ctk q8 and -ctv q8

2

#3 opened 3 months ago by

tientitmu

New activity in stepfun-ai/Step-3.7-Flash-GGUF 3 months ago

Some practical tips for using Step 3.7 GGUFs

🧠👍 2

6

#6 opened 4 months ago by

tarruda

New activity in AesSedai/Step-3.7-Flash-GGUF 3 months ago

PPQ(Q)/PPL(base) and KLD seems significantly worse than Step 3.5 Flash

👀 1

23

#2 opened 4 months ago by

tarruda