Post
2790
Just posted a new article about YandexGPT 5 family of models
https://huggingface.co/blog/WaveCut/yandexgpt5-models-family-digest
https://huggingface.co/blog/WaveCut/yandexgpt5-models-family-digest
Valeriy Selitskiy PRO
WaveCut
AI & ML interests
Looking to switch from hobby to career
Recent Activity
updated a model about 14 hours ago
WaveCut/Qwen3.8-27B-MXFP8-CRACK-NInfer published a model about 14 hours ago
WaveCut/Qwen3.8-27B-MXFP8-CRACK-NInfer liked a model about 22 hours ago
StabilityLabs/Stable-LayersOrganizations
Posts 1
Articles 1
Article
33
Digest of models based on YandexGPT 5 Lite
Five OrbitQuant recipes for fal/ideogram-v4-instant with paired BF16 matrices, metrics, manifests, checksums, and gated licensing.
-
WaveCut/Ideogram-v4-Instant-OrbitQuant-W4A4
Text-to-Image • 5B • Updated • 15 • 1 -
WaveCut/Ideogram-v4-Instant-OrbitQuant-W3A3
Text-to-Image • 4B • Updated • 2 -
WaveCut/Ideogram-v4-Instant-OrbitQuant-W2A4
Text-to-Image • 4B • Updated • 2 • 1 -
WaveCut/Ideogram-v4-Instant-OrbitQuant-W2A3
Text-to-Image • 4B • Updated
Five OrbitQuant recipes for fal/ideogram-v4-instant with paired BF16 matrices, metrics, manifests, checksums, and gated licensing.
-
WaveCut/Ideogram-v4-Instant-OrbitQuant-W4A4
Text-to-Image • 5B • Updated • 15 • 1 -
WaveCut/Ideogram-v4-Instant-OrbitQuant-W3A3
Text-to-Image • 4B • Updated • 2 -
WaveCut/Ideogram-v4-Instant-OrbitQuant-W2A4
Text-to-Image • 4B • Updated • 2 • 1 -
WaveCut/Ideogram-v4-Instant-OrbitQuant-W2A3
Text-to-Image • 4B • Updated
Calibration-free OrbitQuant checkpoints for FLUX.1, FLUX.2 Klein, Z-Image-Turbo, and Wan 2.1 in published low-bit recipes.
spaces 10
Paused
5
Bonsai Chat · WebGPU
🌱
Private 1-bit Bonsai chat, fully local in your browser
Paused
Agents
1
Nemotron-Labs-Audex
🚀
Audio and text demo for NVIDIA Nemotron-Labs-Audex-2B.
Paused
Agents
3
SeFi-Image
🚀
SeFi-Image Base, Turbo, and 5B RL ZeroGPU demo.
Paused
Agents
LTX 2.3 Distilled Upscale IC-LoRA
🎬
Upscale short videos with AI‑enhanced resolution
Paused
Agents
1
LTX-2.3 Video Decompress
🧼
Remove compression artifacts with an LTX-2.3 IC-LoRA
Sleeping
ml-intern sandbox
🌍
models 119
WaveCut/Qwen3.8-27B-MXFP8-CRACK-NInfer
Image-Text-to-Text • Updated • 4
WaveCut/Krea-2-Turbo-OrbitQuant-W4A4
Text-to-Image • 8B • Updated • 42 • 1
WaveCut/Qwen3.8-27B-CRACK-DWQ-4bit-MLX
Image-Text-to-Text • 5B • Updated • 264 • 1
WaveCut/Qwen3.8-27B-MLX-4bit-DWQ
Image-Text-to-Text • 5B • Updated • 748 • 3
WaveCut/DeepSeek-V4-Flash-0731-REAM96-111B-DS4-GGUF
Text Generation • 111B • Updated • 1.06k
WaveCut/DeepSeek-V4-Flash-0731-REAM144-163B-DS4-GGUF
Text Generation • 163B • Updated • 540
WaveCut/DeepSeek-V4-Flash-0731-REAM96-111B
Text Generation • 131B • Updated • 368
WaveCut/DeepSeek-V4-Flash-0731-REAM144-163B
Text Generation • 183B • Updated • 256
WaveCut/DeepSeek-V4-Flash-0731-REAM96-111B-exp-DS4-GGUF
111B • Updated • 189
WaveCut/DeepSeek-V4-Flash-0731-REAM96-111B-exp
Text Generation • 111B • Updated • 98