🏝️ On Vacation
Dmitrii Kostakov
kostakoff
AI & ML interests
MLOps
Recent Activity
liked a model 23 days ago
XiaomiMiMo/MiMo-V2.6-Flash-RL liked a model 23 days ago
XiaomiMiMo/MiMo-V2.6-Pro-RL liked a model about 1 month ago
yandex/AliceAI-Foundation-80B-A3B-BaseOrganizations
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.15M • 1.34k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 4.24M • • 8.39k -
sd2-community/stable-diffusion-2
Text-to-Image • 0.9B • Updated • 2.29k • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 312k • • 2.68k
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 • 59 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 7.78M • • 1.71k -
Qwen/Qwen3-Coder-Next-GGUF
Text Generation • 80B • Updated • 46k • 300 -
mradermacher/gemma-4-26B-A4B-it-heretic-GGUF
25B • Updated • 9.93k • 56
My personal models archive, so I can keep it even if the vendor removes it. It’s very important for my MLOps deployments.
-
zai-org/GLM-5.2
Text Generation • 753B • Updated • 294k • • 5.19k -
deepseek-ai/DeepSeek-V4-Flash-0731
Text Generation • 304B • Updated • 3.89M • • 4.09k -
deepseek-ai/DeepSeek-V4-Pro
Text Generation • 1.6T • Updated • 359k • • 5.68k -
XiaomiMiMo/MiMo-V2.5-Pro
Text Generation • 1T • Updated • 12.3k • • 768
models that can generate video with permissive license
My forks, when I need modify something in original model
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.15M • 1.34k -
suno/bark
Text-to-Speech • Updated • 20k • 1.58k -
suno/bark-small
Text-to-Speech • Updated • 8.25k • 263 -
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Sentence Similarity • 0.1B • Updated • 39.2M • • 1.49k
-
zai-org/GLM-5.2
Text Generation • 753B • Updated • 294k • • 5.19k -
deepseek-ai/DeepSeek-V4-Flash-0731
Text Generation • 304B • Updated • 3.89M • • 4.09k -
deepseek-ai/DeepSeek-V4-Pro
Text Generation • 1.6T • Updated • 359k • • 5.68k -
XiaomiMiMo/MiMo-V2.5-Pro
Text Generation • 1T • Updated • 12.3k • • 768
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.15M • 1.34k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 4.24M • • 8.39k -
sd2-community/stable-diffusion-2
Text-to-Image • 0.9B • Updated • 2.29k • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 312k • • 2.68k
models that can generate video with permissive license
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 • 59 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 7.78M • • 1.71k -
Qwen/Qwen3-Coder-Next-GGUF
Text Generation • 80B • Updated • 46k • 300 -
mradermacher/gemma-4-26B-A4B-it-heretic-GGUF
25B • Updated • 9.93k • 56
My forks, when I need modify something in original model
My personal models archive, so I can keep it even if the vendor removes it. It’s very important for my MLOps deployments.
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.15M • 1.34k -
suno/bark
Text-to-Speech • Updated • 20k • 1.58k -
suno/bark-small
Text-to-Speech • Updated • 8.25k • 263 -
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Sentence Similarity • 0.1B • Updated • 39.2M • • 1.49k