prithivMLmods/vga-qwen3.5-moe-super-gguf
318 GB
Prithiv Sakthi PRO
prithivMLmods
AI & ML interests
computer vision, nlp, multimodality
- HuggingFace Fellowπ€
Recent Activity
upvoted a paper about 3 hours ago
WildDet3D: Scaling Promptable 3D Detection in the Wild upvoted a paper about 3 hours ago
EXAONE 4.5 Technical Report reacted to theirpost with π about 3 hours ago
A new comparator on Spaces showcases Standard FLUX.2 Decoder vs. FLUX.2 Small Decoder. The Small Decoder is ~1.4Γ faster, uses ~1.4Γ less VRAM, and maintains near-identical image quality. It has ~28M parameters with narrower channels [96, 192, 384, 384] vs. [128, 256, 512, 512], and the demo supports sequence generation by running both decoders simultaneously and comparing the results side by side.
π€ Comparator: https://huggingface.co/spaces/prithivMLmods/Flux.2-4B-Decoder-Comparator
π FLUX.2-small-decoder: https://huggingface.co/black-forest-labs/FLUX.2-small-decoder
π GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
π Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
π€ > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.Organizations
Posts 159
Post
48
A new comparator on Spaces showcases Standard FLUX.2 Decoder vs. FLUX.2 Small Decoder. The Small Decoder is ~1.4Γ faster, uses ~1.4Γ less VRAM, and maintains near-identical image quality. It has ~28M parameters with narrower channels [96, 192, 384, 384] vs. [128, 256, 512, 512], and the demo supports sequence generation by running both decoders simultaneously and comparing the results side by side.
π€ Comparator: prithivMLmods/Flux.2-4B-Decoder-Comparator
π FLUX.2-small-decoder: black-forest-labs/FLUX.2-small-decoder
π GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
π Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
π€ > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.
π€ Comparator: prithivMLmods/Flux.2-4B-Decoder-Comparator
π FLUX.2-small-decoder: black-forest-labs/FLUX.2-small-decoder
π GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
π Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
π€ > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.
Articles 16
Article
7
Fine-Tuning MetaCLIP-2 for Image Classification on Downstream Tasks
Collection of Various Compression Schemes for Gemma 4 +MoE Calibration
-
prithivMLmods/gemma-4-26B-A4B-it-FP8_DYNAMIC
Image-Text-to-Text β’ 27B β’ Updated β’ 43 β’ 1 -
prithivMLmods/gemma-4-26B-A4B-it-NVFP4A16
Image-Text-to-Text β’ 16B β’ Updated β’ 144 β’ 2 -
prithivMLmods/gemma-4-26B-A4B-it-MXFP4A16
Image-Text-to-Text β’ 15B β’ Updated β’ 28 β’ 1 -
prithivMLmods/gemma-4-26B-A4B-it-MXFP8A16
Image-Text-to-Text β’ 27B β’ Updated β’ 157 β’ 2
Collection of Uncensored Variants of Gemma 4 Native Multimodal Models
-
prithivMLmods/gemma-4-31B-it-Uncensored-MAX
Image-Text-to-Text β’ 31B β’ Updated β’ 32 β’ 1 -
prithivMLmods/gemma-4-26B-A4B-it-Uncensored-MAX
Image-Text-to-Text β’ 26B β’ Updated β’ 47 β’ 1 -
prithivMLmods/gemma-4-31B-it-Uncensored-MAX-GGUF
Image-Text-to-Text β’ 31B β’ Updated β’ 2.33k β’ 2 -
prithivMLmods/gemma-4-26B-A4B-it-Uncensored-MAX-GGUF
Image-Text-to-Text β’ 25B β’ Updated β’ 3.03k β’ 1
Collection of Various Compression Schemes for Gemma 4 +MoE Calibration
-
prithivMLmods/gemma-4-26B-A4B-it-FP8_DYNAMIC
Image-Text-to-Text β’ 27B β’ Updated β’ 43 β’ 1 -
prithivMLmods/gemma-4-26B-A4B-it-NVFP4A16
Image-Text-to-Text β’ 16B β’ Updated β’ 144 β’ 2 -
prithivMLmods/gemma-4-26B-A4B-it-MXFP4A16
Image-Text-to-Text β’ 15B β’ Updated β’ 28 β’ 1 -
prithivMLmods/gemma-4-26B-A4B-it-MXFP8A16
Image-Text-to-Text β’ 27B β’ Updated β’ 157 β’ 2
Collection of Uncensored Variants of Gemma 4 Native Multimodal Models
-
prithivMLmods/gemma-4-31B-it-Uncensored-MAX
Image-Text-to-Text β’ 31B β’ Updated β’ 32 β’ 1 -
prithivMLmods/gemma-4-26B-A4B-it-Uncensored-MAX
Image-Text-to-Text β’ 26B β’ Updated β’ 47 β’ 1 -
prithivMLmods/gemma-4-31B-it-Uncensored-MAX-GGUF
Image-Text-to-Text β’ 31B β’ Updated β’ 2.33k β’ 2 -
prithivMLmods/gemma-4-26B-A4B-it-Uncensored-MAX-GGUF
Image-Text-to-Text β’ 25B β’ Updated β’ 3.03k β’ 1
spaces 59
pinned
Running on Zero
1
Flux.2 4B Encoder Comparator
β‘
Faster Decoding - (Small Decoder)
pinned
Running on Zero
MCP
9
SAM3-Gemma4-CUDA
β‘
Object Multiplex
pinned
Running on Zero
15
KV Edit Consistency
π€
Fast Editing with Robust Consistency
pinned
Running on Zero
MCP
13
SAM3 + Qwen3.5
πΈ
Multi-object tracking
pinned
Running on Zero
MCP
46
SAM3 Demo
π
Unified foundation model for promptable segmentation
pinned
Running on Zero
33
Qwen 3.5 HF Demo
π€
Demo of the Qwen 3.5 Multimodal Model
models 1,173
prithivMLmods/gemma-4-26B-A4B-it-Uncensored-MAX-GGUF
Image-Text-to-Text β’ 25B β’ Updated β’ 3.03k β’ 1
prithivMLmods/gemma-4-26B-A4B-it-Uncensored-MAX
Image-Text-to-Text β’ 26B β’ Updated β’ 47 β’ 1
prithivMLmods/gemma-4-31B-it-Uncensored-MAX
Image-Text-to-Text β’ 31B β’ Updated β’ 32 β’ 1
prithivMLmods/gemma-4-31B-it-Uncensored-MAX-MLX
Image-Text-to-Text β’ 31B β’ Updated β’ 695 β’ 1
prithivMLmods/gemma-4-31B-it-Uncensored-MAX-GGUF
Image-Text-to-Text β’ 31B β’ Updated β’ 2.33k β’ 2
prithivMLmods/Qwen3.5-35B-A3B-abliterated-v2-MAX
Image-Text-to-Text β’ 35B β’ Updated β’ 2.04k β’ 1
prithivMLmods/gemma-4-26B-A4B-it-FP8_DYNAMIC
Image-Text-to-Text β’ 27B β’ Updated β’ 43 β’ 1
prithivMLmods/gemma-4-26B-A4B-it-NVFP4A16
Image-Text-to-Text β’ 16B β’ Updated β’ 144 β’ 2
prithivMLmods/gemma-4-26B-A4B-it-MXFP4A16
Image-Text-to-Text β’ 15B β’ Updated β’ 28 β’ 1
prithivMLmods/gemma-4-26B-A4B-it-MXFP8A16
Image-Text-to-Text β’ 27B β’ Updated β’ 157 β’ 2
datasets 123
prithivMLmods/Open-Omega-Forge-1M
Viewer β’ Updated β’ 1M β’ 1.28k β’ 6
prithivMLmods/Gacrux-Tiny-1M
Viewer β’ Updated β’ 1.07M β’ 43 β’ 4
prithivMLmods/d.HTML
Viewer β’ Updated β’ 110 β’ 25 β’ 1
prithivMLmods/LAP2-K-Think-v1.b
Viewer β’ Updated β’ 380k β’ 28 β’ 4
prithivMLmods/Pegasus-Tiny-250K
Viewer β’ Updated β’ 292k β’ 49 β’ 2
prithivMLmods/LAP2-K-Think-v1.a
Viewer β’ Updated β’ 257k β’ 66 β’ 2
prithivMLmods/Caption3o-LongCap-v4
Viewer β’ Updated β’ 523k β’ 83 β’ 4
prithivMLmods/Caption3o-XL-v4
Viewer β’ Updated β’ 52.8k β’ 175 β’ 3
prithivMLmods/Turing-Reason-CoT
Viewer β’ Updated β’ 4.99M β’ 54 β’ 6
prithivMLmods/Turing-Reason-CoT-Mini
Viewer β’ Updated β’ 558k β’ 68 β’ 3