32 65 82

www.minds.com/jelyazko/

21world

https://m.youtube.com/@21world

jelspace

AI & ML interests

<Thinking>,<Reasoning> = Schizophrenia . AI AUTOMATION AND ESPIONAGE TOTAL AUTOMATED AI MACHINE CONSTRUCTORS - | BASIC INCOME = FREE MONEY | FOR HUMANS VIA PALLADIUM NEUTRON FUTURES COINS -NEWLY-GENERATED- (AI IS TYPE OF NEURAL FORM)

Recent Activity

updated a collection about 1 hour ago

18\ other models

updated a collection 1 day ago

39\ UPSCALE RESOLUTION

updated a Space 1 day ago

virtual-ic-ai-controller/README

View all activity

Organizations

New activity in NoesisLab/Spartacus-1B-Instruct 4 days ago

ai compare two editions MonoidForCausalLM.py

#2 opened 4 days ago by

21world

New activity in GSAI-ML/ReFusion 2 months ago

many errors in code

#1 opened 2 months ago by

21world

commented a paper 3 months ago

Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 228 •

New activity in taobao-mnn/Qwen3-VL-4B-Instruct-MNN 4 months ago

error when tried usage code

#1 opened 4 months ago by

21world

New activity in amd/RyzenAI-1.5-ESRGAN-Inference-ryzen-strix-cpp 5 months ago

How to get access?

👍 1

#1 opened 5 months ago by

spayno

New activity in inclusionAI/Ring-1T-preview 5 months ago

I would like to use this model on my ipad, but can't find it in the appstore, can someone please help me?

#8 opened 5 months ago by

evewashere

New activity in Efficient-Large-Model/Fast_dLLM_v2_7B 5 months ago

ai generated python code inference with quantization,unable to check is it correct i do not understand python code , runned and seems working .

#1 opened 5 months ago by

21world

New activity in fastllm/Qwen3-Next-80B-A3B-Instruct-UD-Q2_K_S 5 months ago

support via transformers ,probably not gguf,not tested

#1 opened 5 months ago by

21world

New activity in vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 5 months ago

why the int8 and fp16 model size both are 31GB?

🧠 1

#1 opened 5 months ago by

snomile

New activity in Intel/Qwen3-Next-80B-A3B-Instruct-int4-mixed-AutoRound 5 months ago

too slow on cpu

#2 opened 5 months ago by

gopi87

New activity in KVCache-ai/Kimi-K2-Instruct-GGUF 8 months ago

any hope for running on 256gb ram and 12gb vram ?

#3 opened 8 months ago by

gopi87

New activity in institutional/institutional-books-1.0 8 months ago

where are other 128M books????

👍 🧠 2

#3 opened 8 months ago by

21world

where are other 128M books????

👍 🧠 2

#3 opened 8 months ago by

21world

New activity in XiaomiMiMo/MiMo-7B-RL-0530 8 months ago

not the latest tech

#1 opened 9 months ago by

21world

New activity in huihui-ai/Huihui-MoE-4.8B-A1.7B-abliterated 8 months ago

Try moe with different size models!

🧠 1

#1 opened 8 months ago by

21world

New activity in unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF 9 months ago

Super bad performance

😔 1

#5 opened 9 months ago by

DOFOFFICIAL

New activity in unsloth/DeepSeek-R1-0528-GGUF 9 months ago

https://huggingface.co/blog/autoround

#4 opened 9 months ago by

21world

New activity in DevQuasar/deepseek-ai.DeepSeek-R1-0528-GGUF 9 months ago

https://huggingface.co/blog/autoround

👀 1

#1 opened 9 months ago by

21world

New activity in ubergarm/DeepSeek-R1-0528-GGUF 9 months ago

https://huggingface.co/blog/autoround

#1 opened 9 months ago by

21world

www.minds.com/jelyazko/

AI & ML interests

Recent Activity

Organizations

21world's activity

ai compare two editions MonoidForCausalLM.py

many errors in code

error when tried usage code

How to get access?

I would like to use this model on my ipad, but can't find it in the appstore, can someone please help me?

ai generated python code inference with quantization,unable to check is it correct i do not understand python code , runned and seems working .

support via transformers ,probably not gguf,not tested

why the int8 and fp16 model size both are 31GB?

too slow on cpu

any hope for running on 256gb ram and 12gb vram ?

where are other 128M books????

where are other 128M books????

not the latest tech

Try moe with different size models!

Super bad performance

https://huggingface.co/blog/autoround

https://huggingface.co/blog/autoround

https://huggingface.co/blog/autoround