-
zai-org/GLM-5.2
Text Generation • 753B • Updated • 2.49M • • 4.91k -
deepseek-ai/DeepSeek-V4-Flash-0731
Text Generation • 304B • Updated • 869k • • 2.92k -
deepseek-ai/DeepSeek-V4-Pro
Text Generation • 1.6T • Updated • 1.48M • • 5.4k -
XiaomiMiMo/MiMo-V2.5-Pro
Text Generation • 1T • Updated • 58.4k • • 731
Dmitrii Kostakov PRO
kostakoff
AI & ML interests
MLOps
Recent Activity
updated a collection about 12 hours ago
very cool but I can't run them locally liked a model about 12 hours ago
XiaomiMiMo/MiMo-V2.5-Pro-Base updated a collection 2 days ago
very cool but I can't run them locally Organizations
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 • 1.46M • 1.23k -
suno/bark
Text-to-Speech • Updated • 40.2k • 1.55k -
suno/bark-small
Text-to-Speech • Updated • 109k • 261 -
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Sentence Similarity • 0.1B • Updated • 55.8M • • 1.34k
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.46M • 1.23k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 1.39M • • 8.03k -
sd2-community/stable-diffusion-2
Text-to-Image • 0.9B • Updated • 1.78k • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 187k • • 2.57k
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 • 22 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 10.4M • • 1.37k -
Qwen/Qwen3-Coder-Next-GGUF
Text Generation • 80B • Updated • 23.7k • 273 -
mradermacher/gemma-4-26B-A4B-it-heretic-GGUF
25B • Updated • 8.6k • 47
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 • 2.49M • • 4.91k -
deepseek-ai/DeepSeek-V4-Flash-0731
Text Generation • 304B • Updated • 869k • • 2.92k -
deepseek-ai/DeepSeek-V4-Pro
Text Generation • 1.6T • Updated • 1.48M • • 5.4k -
XiaomiMiMo/MiMo-V2.5-Pro
Text Generation • 1T • Updated • 58.4k • • 731
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.46M • 1.23k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 1.39M • • 8.03k -
sd2-community/stable-diffusion-2
Text-to-Image • 0.9B • Updated • 1.78k • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 187k • • 2.57k
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 • 22 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 10.4M • • 1.37k -
Qwen/Qwen3-Coder-Next-GGUF
Text Generation • 80B • Updated • 23.7k • 273 -
mradermacher/gemma-4-26B-A4B-it-heretic-GGUF
25B • Updated • 8.6k • 47
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 • 1.46M • 1.23k -
suno/bark
Text-to-Speech • Updated • 40.2k • 1.55k -
suno/bark-small
Text-to-Speech • Updated • 109k • 261 -
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Sentence Similarity • 0.1B • Updated • 55.8M • • 1.34k