Dmitrii Kostakov PRO
kostakoff
AI & ML interests
MLOps
Recent Activity
liked a model 2 days ago
yandex/AliceAI-Foundation-80B-A3B-Base liked a model 11 days ago
tencent/Hy4-preview updated a collection 11 days ago
very cool but I can't run them locally Organizations
I found interesting
open image generation
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.83M • 1.28k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 3.4M • • 8.22k -
sd2-community/stable-diffusion-2
Text-to-Image • 0.9B • Updated • 4.18k • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 297k • • 2.66k
best for dgx spark
my personal test, to figure out which models are best for nvidia dgx spark
-
kostakoff/Mixtral-8x7B-Instruct-v0.1-GGUF
Text Generation • 47B • Updated • 53 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 10.5M • • 1.54k -
Qwen/Qwen3-Coder-Next-GGUF
Text Generation • 80B • Updated • 20.6k • 280 -
mradermacher/gemma-4-26B-A4B-it-heretic-GGUF
25B • Updated • 21.3k • 55
archive
My personal models archive, so I can keep it even if the vendor removes it. It’s very important for my MLOps deployments.
very cool but I can't run them locally
open tts generation
open video generation
models that can generate video with permissive license
Forks
My forks, when I need modify something in original model
favorite
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.83M • 1.28k -
suno/bark
Text-to-Speech • Updated • 30.2k • 1.56k -
suno/bark-small
Text-to-Speech • Updated • 28.4k • 262 -
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Sentence Similarity • 0.1B • Updated • 46M • • 1.41k
interesting but custom license
very cool but I can't run them locally
I found interesting
open tts generation
open image generation
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.83M • 1.28k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 3.4M • • 8.22k -
sd2-community/stable-diffusion-2
Text-to-Image • 0.9B • Updated • 4.18k • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 297k • • 2.66k
open video generation
models that can generate video with permissive license
best for dgx spark
my personal test, to figure out which models are best for nvidia dgx spark
-
kostakoff/Mixtral-8x7B-Instruct-v0.1-GGUF
Text Generation • 47B • Updated • 53 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 10.5M • • 1.54k -
Qwen/Qwen3-Coder-Next-GGUF
Text Generation • 80B • Updated • 20.6k • 280 -
mradermacher/gemma-4-26B-A4B-it-heretic-GGUF
25B • Updated • 21.3k • 55
Forks
My forks, when I need modify something in original model
archive
My personal models archive, so I can keep it even if the vendor removes it. It’s very important for my MLOps deployments.
favorite
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.83M • 1.28k -
suno/bark
Text-to-Speech • Updated • 30.2k • 1.56k -
suno/bark-small
Text-to-Speech • Updated • 28.4k • 262 -
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Sentence Similarity • 0.1B • Updated • 46M • • 1.41k