Eva Winterschön PRO
winterschon
AI & ML interests
Quantizing, Querying, Sublimating, Subsuming, Subversifying, and Generally Questioning Everything
Recent Activity
upvoted an article 6 days ago
Granite 4.1 LLMs: How They’re Built liked a model 29 days ago
ibm-granite/granite-4.1-8b updated a collection 29 days ago
RAG Specialized Organizations
-
nanonets/Nanonets-OCR-s
Image-Text-to-Text • 4B • Updated • 23.2k • 1.59k -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 263 • 399 -
PleIAs/Pleias-RAG-1B-gguf
1B • Updated • 132 • 13 -
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 2.94k • 46
-
gorilla-llm/gorilla-openfunctions-v2
Text Generation • Updated • 155 • 245 -
deepseek-ai/DeepSeek-V2.5
Text Generation • 236B • Updated • 5.9k • 734 -
BeaverAI/Fallen-Gemma3-4B-v1g-GGUF
4B • Updated • 12 • 2 -
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 2.94k • 46
-
A guide to convolution arithmetic for deep learning
Paper • 1603.07285 • Published • 1 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 48 -
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Paper • 2606.09079 • Published • 67 -
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Paper • 2603.19312 • Published • 50
-
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Text Generation • 32B • Updated • 613k • 355 -
nvidia/Qwen3-235B-A22B-NVFP4
Text Generation • 133B • Updated • 173k • 19 -
Qwen/Qwen3-235B-A22B
Text Generation • 235B • Updated • 695k • • 1.11k -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • 235B • Updated • 1.19k • 5
-
On-Device LLM Throughput Calculator
🚀21Generate throughput plot for LLMs on devices
-
UNO FLUX
⚡788Generate customized images using text and multiple images
-
Open LLM Leaderboard Model Comparator
🏆113Compare Open LLM Leaderboard results
-
Open LLM Leaderboard
🏆14.1kTrack, rank and evaluate open LLMs and chatbots
-
gorilla-llm/gorilla-openfunctions-v2-gguf
7B • Updated • 425 • 45 -
BeaverAI/Fallen-Gemma3-4B-v1g-GGUF
4B • Updated • 12 • 2 -
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 2.94k • 46 -
mlabonne/gemma-3-12b-it-abliterated-GGUF
Image-Text-to-Text • 12B • Updated • 1.85k • 55
-
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Text Generation • 32B • Updated • 613k • 355 -
nvidia/Qwen3-235B-A22B-NVFP4
Text Generation • 133B • Updated • 173k • 19 -
Qwen/Qwen3-235B-A22B
Text Generation • 235B • Updated • 695k • • 1.11k -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • 235B • Updated • 1.19k • 5
-
nanonets/Nanonets-OCR-s
Image-Text-to-Text • 4B • Updated • 23.2k • 1.59k -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 263 • 399 -
PleIAs/Pleias-RAG-1B-gguf
1B • Updated • 132 • 13 -
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 2.94k • 46
-
On-Device LLM Throughput Calculator
🚀21Generate throughput plot for LLMs on devices
-
UNO FLUX
⚡788Generate customized images using text and multiple images
-
Open LLM Leaderboard Model Comparator
🏆113Compare Open LLM Leaderboard results
-
Open LLM Leaderboard
🏆14.1kTrack, rank and evaluate open LLMs and chatbots
-
gorilla-llm/gorilla-openfunctions-v2-gguf
7B • Updated • 425 • 45 -
BeaverAI/Fallen-Gemma3-4B-v1g-GGUF
4B • Updated • 12 • 2 -
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 2.94k • 46 -
mlabonne/gemma-3-12b-it-abliterated-GGUF
Image-Text-to-Text • 12B • Updated • 1.85k • 55
-
gorilla-llm/gorilla-openfunctions-v2
Text Generation • Updated • 155 • 245 -
deepseek-ai/DeepSeek-V2.5
Text Generation • 236B • Updated • 5.9k • 734 -
BeaverAI/Fallen-Gemma3-4B-v1g-GGUF
4B • Updated • 12 • 2 -
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 2.94k • 46
-
A guide to convolution arithmetic for deep learning
Paper • 1603.07285 • Published • 1 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 48 -
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Paper • 2606.09079 • Published • 67 -
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Paper • 2603.19312 • Published • 50