Hugging Face's logo
DavidAU 's Collections
Dark Planet Series (see "source" coll. for FP)
Grand Horror 16.5B+ Horror and Fiction Generation
Dark / Evil / NSFW Reasoning Models (gguf/source)
200+ Roleplay, Creative Writing, Uncensored, NSFW models.
Qwen3 - 30B-A3B (128 experts) and higher
Qwen3 - 16B-A3B - 64 experts + Brainstorm versions
Thinking / Reasoning Models - Reg and MOEs.
MOE - Reasoning - Gated IQ Multi-Tier Models
MOE/Mixture of Experts Models (see also "source" cll)
Qwen 3 / 2.5 Reasoning/Thinking REG + MOEs.
Qwen 3 - Horror / Neo Imatrix / Max Qs / 32-256k ctx
Dark Planet Wordstorm Project - Random Prune / Form.
Gemma The Writer Series - GGUF / Source)
Gemma3 - Modified / Augumented Models
Rogue Creative Series - GGUF / Incl Source too.
Brainstorm - Augmented and Expanded Reasoning
Reasoning Adapters / LORAs -> Any model to reasoning
Reasoning Source files for GGUF, EXL2, AWQ, GPTQ
Source files for GGUF, EXL2, AWQ, GPTQ, HQQ etc etc
WS - Qwen3 4B - Fiction on Fire - Merge/pruning series.
WS - Wordstorm 10 Part Series incl Full Source
David's Software, DOCs and How To for Models.
Higher Precision GGUFs / Imatrix Plus
X-Quants - State of Mind Adjusted Quants
Mini-MOEs - Mixture of Experts 2x, x4 and x8
Solar Models (Q6) - Exceptional Performance
Long Context - 16k,32k,64k,128k,200k,256k,512k,1000k
Instruct Models - Better instruction following.
10B / 10.7B / 11B models (except MOEs)
Experiments in Merging Top Models
1b,3b,4b - Upgraded Quants Q6/Q8
High Quality / Hard to Find
50 Leaderboards, Benchs, GGUF Tools, and Utilities
2000+ Run LLMs here - Directly in your browser
31 - Run Image / Video LLMs in your browser

MOE/Mixture of Experts Models (see also "source" cll)

Mixture of Expert Models by me. This leverages the power of multiple models at the same time during generation for next level performance.

Upvote
9