Mini-MOEs - Mixture of Experts 2x, x4 and x8 - a DavidAU Collection

DavidAU 's Collections

D_AU - Dark Planet Series (see "source" coll. for FP)

D_AU - Grand Horror 16.5B+ Horror and Fiction Generation

D_AU- MOE/Mixture of Experts Models (see also "source" coll)

D_AU - Gemma The Writer Series - GGUF / Source)

D_AU - Reasoning / Deepseek Models with "thinking/reasoning"

D_AU - Reasoning Adapters / LORAs -> Any model to reasoning

D_AU - Reasoning Source files for GGUF, EXL2, AWQ, GPTQ

D_AU - Rogue Creative Series - GGUF / Incl Source too.

D_AU - Brainstorm - Augmented and Expanded Reasoning

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

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

D_AU - Source files for GGUF, EXL2, AWQ, GPTQ, HQQ etc etc

D_AU - Wordstorm 10 Part Series incl Full Source

D_AU - Higher Precision GGUFs / Imatrix Plus

D_AU - X-Quants - State of Mind Adjusted Quants

D_AU - Experiments in Merging Top Models

Mini-MOEs - Mixture of Experts 2x, x4 and x8

Long Context - 16k,32k,64k,128k,200k,256k,512k,1000k

Instruct Models - Better instruction following.

Solar Models (Q6) - Exceptional Performance

1b,3b,4b - Upgraded Quants Q6/Q8

10B / 10.7B / 11B models (except MOEs)

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

Mini-MOEs - Mixture of Experts 2x, x4 and x8

updated 2 days ago

Tiny but mighty. 1B, 1.1B, 2B (2x,x4,x8) MOE models. Suggest Q8 version, and review of original model page for template (!), usage & help.