sakuma

sakumaXIII

·

AI & ML interests

None yet

Recent Activity

liked a Space about 6 hours ago

overhead520/Unhinged-ERP-Benchmark

liked a model about 13 hours ago

SerialKicked/ModelTestingBed

liked a model about 23 hours ago

Naphula/Goetia-26B-A4B-v1.6

View all activity

Organizations

None yet

upvoted 3 collections about 1 month ago

J.O.S.I.E-2

The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 22 items • Updated Aug 7 • 11

Qwen3.8

4 items • Updated Aug 13 • 520

Muse Glimmer

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated Aug 10 • 108

upvoted 3 collections about 2 months ago

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 28 days ago • 394

Norovox Alpha Series

Ozgun mimari ile Ucretsiz bulutta egitildi. • 7 items • Updated Jul 25 • 2

Moshi v0.1 Release

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 16 items • Updated Jul 15 • 246

upvoted an article about 2 months ago

Article

Security incident disclosure — July 2026

system

•

Jul 16

• 791

upvoted 5 collections 3 months ago

Guilherme34 Best Models

this is the best models i have ever made • 8 items • Updated Aug 10 • 2

Models

Some stuff that's kinda usable • 2 items • Updated May 24 • 1

Favorite Uncensored Drivers

These models have no refusals and require no jailbreaks. • 62 items • Updated 2 days ago • 26

Portfolio 2026

11 items • Updated 4 days ago • 24

Other stuff

12 items • Updated Jun 21 • 2

upvoted an article 3 months ago

Article

Norm-Preserving Biprojected Abliteration

grimjim

•

Nov 6, 2025

• 98

upvoted 7 collections 3 months ago

Latest Releases

Finetuned by yours truly. • 14 items • Updated 8 days ago • 10

DiffusionGemma

1 item • Updated Jul 21 • 64

Unsloth Diffusion GGUFs

Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX. • 20 items • Updated 21 days ago • 104

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 121 items • Updated 17 days ago • 830

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 21 days ago • 264

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 21 days ago • 121

Gemma 4 QAT Mobile

4 items • Updated Jul 21 • 53