Thiago de Arruda Padilha

tarruda's activity

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

New activity in AesSedai/Qwen3.5-397B-A17B-GGUF 5 days ago

MTP support merged in llama.cpp

13

#10 opened 8 days ago by

tarruda

New activity in ubergarm/Kimi-K2.6-GGUF 5 days ago

MTP Support

👍 2

9

#13 opened 8 days ago by

anikifoss

New activity in antirez/deepseek-v4-gguf 11 days ago

Suggestion: Add IQ3 variants.

👍 2

4

#7 opened 12 days ago by

tarruda

New activity in AesSedai/MiMo-V2.5-GGUF 12 days ago

Any llama.cpp parameters to work around the looping?

👍 1

2

#12 opened 12 days ago by

tarruda

Can you share the command you used to create the BF16 ggus?

2

#10 opened 15 days ago by

tarruda

New activity in AesSedai/MiMo-V2.5-GGUF 16 days ago

IQ3_S doesn't load with "wrong number of tensors"

2

#9 opened 16 days ago by

tarruda

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF 17 days ago

Can the MTP version currently be loaded in LM Studio?

❤️👍 3

5

#2 opened 18 days ago by

cclongdevil

New activity in llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF 19 days ago

Excellent work on this one

2

#8 opened 19 days ago by

tarruda

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2 19 days ago

Keep the mtp layer weight

👍 2

10

#5 opened 21 days ago by

Light4Bear

New activity in bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF 20 days ago

Seems like chat template is broken?

4

#3 opened 23 days ago by

tarruda

New activity in Qwen/Qwen3.6-35B-A3B about 1 month ago

Where's 397b?

👀 10

5

#7 opened about 1 month ago by

ebfio

New activity in AesSedai/MiniMax-M2.7-GGUF about 1 month ago

nan kld

10

#4 opened about 1 month ago by

krampenschiesser

New activity in p-e-w/gpt-oss-20b-heretic-ara-v4 about 1 month ago

Any plans for gpt-oss-120b?

1

#2 opened about 1 month ago by

tarruda

New activity in tarruda/Qwen3.5-397B-A17B-GGUF about 1 month ago

What are your tokens/s? And what about rewriting MiniMax m2.7? Great work man!

3

#2 opened about 1 month ago by

Arkovski

New activity in tarruda/Qwen3.5-397B-A17B-GGUF about 2 months ago

Great job on this one!

2

#1 opened about 2 months ago by

ubergarm

New activity in AesSedai/Qwen3.5-397B-A17B-GGUF about 2 months ago

IQ2_XS?

🔥 2

30

#6 opened 2 months ago by

tarruda

New activity in ArliAI/Qwen3.5-27B-Derestricted 2 months ago

Nice!

#3 opened 2 months ago by

tarruda

New activity in llmfan46/Q3.5-BlueStar-v2-27B-uncensored-heretic 2 months ago

Impressive work!

👍 1

1

#1 opened 2 months ago by

tarruda

New activity in tarruda/Qwen3.5-397B-A17B-heretic-smol-IQ2_XS-GGUF 2 months ago

Any chance of IQ2_XXS? IQ2_XS is just slightly too big for Strix Halo.

6

#2 opened 2 months ago by

Cortex0833

imatrix source

3

#1 opened 2 months ago by

coughmedicine