AsThirtyThree

P(doom) <0.001%

AI & ML interests

i will marry with iq4xs quantization soon, i love qwen and gemma, my favorite video model is minimax h3 and i love fine tuners

Recent Activity

liked a model about 13 hours ago

AtomicChat/Qwen3.8-27B-GGUF

upvoted a changelog about 14 hours ago

Decision Models on the Hub

liked a model about 22 hours ago

JetBrains/Mellum2.1-12B-A2.5B-Thinking

View all activity

Organizations

None yet

New activity in peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP 9 days ago

Cyber-Tiel-Coder-35B is great! 27B?

❤️ 2

#18 opened 12 days ago by

RTODie

New activity in peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF 14 days ago

im waiting for k2 horizon mova 36b a4b

#1 opened 14 days ago by

AsThirtyThree

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 17 days ago

Delete Ternary-Bonsai-2-27B-PQ2_0.gguf

#72 opened 17 days ago by

Lizpp

New activity in Agnes-AI/Agnes-3.0-Flash 27 days ago

Its Dense model and only slightly better than Qwen3.6 MOE....

👀 3

#3 opened about 1 month ago by

Pumba2

New activity in openbmb/MiniCPM5-2B 27 days ago

it will be good if model supports turkish

#8 opened about 1 month ago by

AsThirtyThree

New activity in deepseek-ai/DeepSeek-V4.1-Flash 30 days ago

OpenAI and Claude don't make me download half a terabyte of weight just to ask a question smh

🧠🤯 33

#18 opened about 1 month ago by

Mikkkkoooo

New activity in peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF about 1 month ago

This model is COOKING HARD

🔥❤️ 1

#10 opened about 1 month ago by

nmh2k3

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

Qwen3.8 35B-A5B PLS

😔❤️ 60

#1 opened about 2 months ago by

highpolygonal

New activity in peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF about 1 month ago

wow,my man uploaded another peak model

❤️ 1

#2 opened about 1 month ago by

AsThirtyThree

New activity in peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP about 1 month ago

its THE model for 8gb vram users

❤️ 1

#11 opened about 2 months ago by

Gamination

New activity in yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF about 1 month ago

Progress update on v3?

#64 opened 3 months ago by

Lihanvdwes

New activity in zai-org/GLM-5.3-Flash about 2 months ago

WE NEED 35B A3B

👍🔥 19

#3 opened about 2 months ago by

AsThirtyThree

New activity in Qwen/Qwen3.8-Flash-Next about 2 months ago

50b moe?

🔥 15

#11 opened about 2 months ago by

vonamakitsune

New activity in Kijai/MiniMax-H3_comfy about 2 months ago

I did some testing and I am confused

#18 opened about 2 months ago by

AbsAnon

New activity in Lightricks/LTX-2.5 about 2 months ago

Any chance for a bigger text encoder (e.g. Gemma 4 26b) for the next version?

👍 2

#62 opened about 2 months ago by

kabachuha

New activity in Trendyol/Trendyol-LLM-8B-T1 about 2 months ago

türkçe bir CoT modeli olduğunu bilmiyordum

❤️ 1

#1 opened about 2 months ago by

AsThirtyThree

New activity in peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF about 2 months ago

innnnnnnnnnnnnteresting

👍 1

#4 opened about 2 months ago by

AsThirtyThree

New activity in empero-ai/Qwen3.8-27B-Ridge-GGUF about 2 months ago

im fast,im here

❤️ 3

#1 opened about 2 months ago by

AsThirtyThree

New activity in peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF about 2 months ago

yo,a peak model again!

❤️ 1

#8 opened about 2 months ago by

AsThirtyThree

New activity in unsloth/Qwen3.8-27B-GGUF about 2 months ago

Qwen in the UD-IQ3_XXS quant is honestly pretty impressive on my RTX 5070 Ti with 32 GB of 6400 MT/s RAM.

🚀 1

#94 opened about 2 months ago by

Nevermorye

AsThirtyThree

AI & ML interests

Recent Activity

Organizations

AsThirtyThree's activity

Cyber-Tiel-Coder-35B is great! 27B?

im waiting for k2 horizon mova 36b a4b

Delete Ternary-Bonsai-2-27B-PQ2_0.gguf

Its Dense model and only slightly better than Qwen3.6 MOE....

it will be good if model supports turkish

OpenAI and Claude don't make me download half a terabyte of weight just to ask a question smh

This model is COOKING HARD

Qwen3.8 35B-A5B PLS

wow,my man uploaded another peak model

its THE model for 8gb vram users

Progress update on v3?

WE NEED 35B A3B

50b moe?

I did some testing and I am confused

Any chance for a bigger text encoder (e.g. Gemma 4 26b) for the next version?

türkçe bir CoT modeli olduğunu bilmiyordum

innnnnnnnnnnnnteresting

im fast,im here

yo,a peak model again!

Qwen in the UD-IQ3_XXS quant is honestly pretty impressive on my RTX 5070 Ti with 32 GB of 6400 MT/s RAM.