Because there is a 'single' R and a 'double' R, so I guess these are two subtypes of 'R' lmao. (Seriously, I'd be kinda amused if that's how the model is looking upon it.)

liked 2 models 10 months ago

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

Text Generation • 253B • Updated Oct 15, 2025 • 1.31k • • 343

DevQuasar/nvidia.Llama-3_1-Nemotron-Ultra-253B-v1-GGUF

Text Generation • 253B • Updated Apr 16, 2025 • 59 • 7

New activity in Gryphe/Pantheon-RP-1.0-8b-Llama-3 over 1 year ago

Great Model

#1 opened over 1 year ago by

spike4379

New activity in sophosympatheia/Midnight-Rose-70B-v2.0.3 almost 2 years ago

Scores very highly on EQ Bench!

❤️ 1

#3 opened almost 2 years ago by

BoshiAI

New activity in Chat-Error/Mythalion-Kimiko-v2 about 2 years ago

Now Available in GGUF, AWG & GPTQ format!

#2 opened about 2 years ago by

BoshiAI

New activity in actionpace/Mythalion-Kimiko-v2 about 2 years ago

How come nobody noticed this!?

❤️ 2

#1 opened about 2 years ago by

BoshiAI

New activity in Chat-Error/Mythalion-Kimiko-v2 about 2 years ago

Mythalion (enhanced MythoMax) with Kimiko AND a 8K context buffer? Why no discussion !?

#1 opened about 2 years ago by

BoshiAI

New activity in athirdpath/Iambe-RP-cDPO-20b-GGUF about 2 years ago

Iambe v2 vs Iambe v3

#2 opened about 2 years ago by

anmol989

Boshi

AI & ML interests

Recent Activity

Organizations

BoshiAI's activity

Could you quantify the UD-TQ1_0 model of GLM-4.7-PRISM?

Model download

Will GLM-4.6-Air model be released?

Thanks & Feedback

Thank you!! (IQ quants)

Nemotron 253B?

Great Model

Scores very highly on EQ Bench!

Now Available in GGUF, AWG & GPTQ format!

How come nobody noticed this!?

Mythalion (enhanced MythoMax) with Kimiko AND a 8K context buffer? Why no discussion !?

Iambe v2 vs Iambe v3