LFM 1.2B SOTA- 400-700 T/S - Enhanced/Fine Tunes // Distills

DavidAU 's Collections

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

Grand Horror 16.5B+ Horror and Fiction Generation

Dark MOEs - Mixture of Experts - Uncensored Creative Models

Dark Champion Collection MOE - Mixture Of Experts

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

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Dark / Evil / NSFW Reasoning Models (gguf/source)

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Claude Fine Tune Distills - 1B to 42B - reg / uncensored.

GLM 4.7 Flash Distill Finetunes - 1B to 32B - reg/uncensored

Gemini Distills 1B to 32B - Reg and Uncensored

Gemma 3 - Reasoning/Thinking Models (incl uncensored)

LFM 1.2B SOTA- 400-700 T/S - Enhanced/Fine Tunes // Distills

Gemma The Writer Series - GGUF / Source)

OpenAI-GPT 20B, 37B ,120B: Neo, reg, uncensored, ablit.

Qwen 3 - Horror / Neo Imatrix / Max Qs / 32-256k ctx

Brainstorm Adapter Models - Augmented/Expanded Reasoning

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

Coders and Programmers: 128 expert / A3B Coders

Coders and Programmers: 4B Models with Brainstorm 20x (6B)

Coders and Programmers: 0.8B, 2.4B, 3.4B

Qwen3 - 30B-A3B (128 experts) and higher

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.

Gemma3 - Modified / Augumented Models

Rogue Creative Series - GGUF / Incl Source too.

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

Higher Precision GGUFs / Imatrix Plus

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

Instruct Models - Better instruction following.

WS - Dark Planet Wordstorm Project - Random Prune / Form.

WS - Wordstorm 10 Part Series incl Full Source

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

Reasoning Source files for GGUF, EXL2, AWQ, GPTQ

Experiments in Merging Top Models

Older Models - High Quality / Hard to Find

LFM 1.2B SOTA- 400-700 T/S - Enhanced/Fine Tunes // Distills

updated 9 days ago

Fine tunes of LFM 1.2B (SOTA) models via Unsloth to enhance performance, including reasoning/thinking distills and "reasoning/thinking" replacements.

Upvote

DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning

Text Generation • 1B • Updated Feb 3 • 233 • 13
DavidAU/LFM2.5-1.2B-MEGABRAIN-Thinking-Claude-Polaris-Deepseek-GLM

Text Generation • 1B • Updated Feb 6 • 82 • 9
DavidAU/LFM2.5-1.2B-Thinking-Claude-4.6-Opus-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated 30 days ago • 418 • 5

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-MEGABRAIN2-Thinking-Kimi-V2-DISTILL

Text Generation • 1B • Updated Feb 7 • 347 • 4
DavidAU/LFM2.5-1.2B-Polaris-Alpha-Thinking-DISTILL

Text Generation • 1B • Updated Feb 6 • 6 • 2
DavidAU/LFM2.5-1.2B-Deepseek-3.1-Thinking-DISTILL

Text Generation • 1B • Updated Feb 6 • 11 • 2
DavidAU/LFM2.5-1.2B-Thinking-Claude-4.5-Opus-High-Reasoning

Text Generation • 1B • Updated Feb 6 • 34 • 2
DavidAU/LFM2.5-1.2B-MEGABRAIN-Thinking-Polaris-ClaudeHOPUS-Deepseek-GLM

Text Generation • 1B • Updated Feb 6 • 7 • 2
DavidAU/LFM2.5-1.2B-Thinking-GLM-4.7-Flash-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 27 • 2

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-GLM-4.7-Flash-Thinking

Text Generation • 1B • Updated Feb 6 • 13 • 1
DavidAU/LFM2.5-1.2B-Thinking-Claude-4.5-Opus-High-Reasoning-IRONMAN

Text Generation • 1B • Updated Feb 6 • 8 • 1
DavidAU/LFM2.5-1.2B-Thinking-Claude-4.5-Opus-DISTILL

Text Generation • 1B • Updated Feb 16 • 6 • 1
DavidAU/LFM2.5-1.2B-Thinking-TRI-Gemini-Multi-DISTILL

Text Generation • 1B • Updated Feb 16 • 9 • 1
DavidAU/LFM2.5-1.2B-Thinking-SuperMinds-7x-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 15 • 3

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-Thinking-GPT-5.1-1000-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 10 • 1

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-Thinking-Kimi-V2-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 34 • 2

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-Thinking-Gemini-Pro-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 11 • 1

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-Thinking-Polaris-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 5 • 1

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-Thinking-Deepseek-3.1-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 41 • 1

Note Fully Uncensored first, then fine tuned for max performance.
DavidAU/LFM2.5-1.2B-Thinking-Gemini-Pro-1000-Heretic-Uncensored-DISTILL

Text Generation • 1B • Updated Feb 16 • 20 • 4

Note Fully Uncensored first, then fine tuned for max performance.

Upvote