Rauno Ryystö

raunoryys

·

AI & ML interests

None yet

Recent Activity

liked a model about 1 hour ago

TheDrummer/Orion-26B-A4B-v1

liked a model about 2 hours ago

tencent/Hy4-preview-FP8

upvoted a collection about 2 hours ago

View all activity

Organizations

None yet

upvoted a collection about 2 hours ago

Hy4 preview

2 items • Updated about 3 hours ago • 4

upvoted a paper 1 day ago

A Programming Paradigm for Spatiotemporal Composability

Paper • 2608.25512 • Published 2 days ago • 11

upvoted a collection 2 days ago

Qwen3.8-Flash-Next

2 items • Updated 2 days ago • 36

upvoted a collection 3 days ago

WeMM-Embedding

4 items • Updated 2 days ago • 21

upvoted a paper 3 days ago

MobileMoE: Scaling On-Device Mixture of Experts

Paper • 2605.27358 • Published May 26 • 17

upvoted a collection 3 days ago

MobileMoE

a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier • 11 items • Updated about 6 hours ago • 6

upvoted a collection 7 days ago

Qwen3.8 27B Uncensored / Abliterated

The Qwen3.8-27B-Uncensored family from OrcaRouter 🐋 FP8 ✅ NVFP4 ✅ GGUF ✅ INT8 ✅ MLX ✅ Full precision ✅ • 6 items • Updated 8 days ago • 61

upvoted a collection 8 days ago

Mini-Me

Smaller versions of open weights models • 3 items • Updated 8 days ago • 4

upvoted an article 13 days ago

Article

State of Open Models: Summer 2026 Observations

+1

AdinaY, multimodalart, irenesolaiman

•

14 days ago

• 165

upvoted a collection 13 days ago

dots3.note

2 items • Updated 14 days ago • 11

upvoted 2 collections 14 days ago

NVFP4

Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 11 items • Updated 1 day ago • 65

UI-Mate

3 items • Updated 3 days ago • 21

upvoted a collection 15 days ago

Qwen3.8

4 items • Updated 15 days ago • 449

upvoted a paper 15 days ago

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 40

upvoted a collection 15 days ago

Qwen3.8

Qwen3.8 Unsloth quants including Qwen3.8-27B! Run and train Qwen3.8 with the Unsloth Desktop app. • 10 items • Updated 1 day ago • 69

upvoted a paper 15 days ago

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 164

upvoted 2 collections 15 days ago

MiniMax-M3

7 items • Updated 13 days ago • 21

👁️ LFM2.5-VL

9 items • Updated 16 days ago • 54

upvoted 2 articles 16 days ago

Article

Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis

allenai

•

16 days ago

• 16

Article

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

CohereLabs

•

16 days ago

• 38