SPREEK

spreek

·

AI & ML interests

None yet

Recent Activity

upvoted a collection about 2 months ago

Sentence Transformers v5.4 integrations

upvoted a collection 3 months ago

liked a Space 3 months ago

ggml-org/gguf-my-repo

View all activity

Organizations

None yet

upvoted a collection about 2 months ago

Sentence Transformers v5.4 integrations

See https://huggingface.co/blog/multimodal-sentence-transformers • 40 items • Updated about 9 hours ago • 10

upvoted a collection 3 months ago

Android Models

LiteRT models that can run on Android • 17 items • Updated 3 days ago • 283

liked a Space 3 months ago

GGUF My Repo

Quantize a Hugging Face model into GGUF format

upvoted 2 collections 3 months ago

Thinking / Reasoning Models - Reg and MOEs.

QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 114 items • Updated 4 days ago • 29

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 140 items • Updated about 13 hours ago • 184

liked a model 3 months ago

OS-Copilot/OS-Shepherd-9B

Image-Text-to-Text • 9B • Updated Aug 7 • 85 • 4

upvoted 3 collections 3 months ago

David's Software, DOCs and How To for Models.

Software and How to cover some of my models specifically and can be applied to all models / all repos too. • 6 items • Updated 20 days ago • 16

100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused.

Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 82 items • Updated about 13 hours ago • 73

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 490 items • Updated about 5 hours ago • 106

liked 7 models 3 months ago

mradermacher/MicroThinker-8B-Preview-GGUF

8B • Updated Jan 26, 2025 • 392 • 2

huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 4.49k • • 75

huihui-ai/Huihui-gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF

Any-to-Any • 7B • Updated Jun 11 • 17.9k • 30

huihui-ai/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF

Any-to-Any • 12B • Updated Jun 8 • 46.5k • 73

jwest33/qwen3-vl-8b-instruct-null-space-abliterated-GGUF

8B • Updated Dec 22, 2025 • 680 • 8

llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GGUF

Image-Text-to-Text • 27B • Updated May 25 • 6.43k • 48

llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF

Image-Text-to-Text • 35B • Updated May 29 • 39.3k • 128

liked 3 Spaces 3 months ago

Coding Agent Leaderboard

Compare coding agent models + harnesses

Low-bit LLM Leaderboard

Track, rank and evaluate open LLMs and chatbots

MTEB Leaderboard

Embedding Leaderboard

upvoted a collection 3 months ago

Recent medium models

100 items • Updated 2 days ago • 19