Adam Fields

adamelliotfields's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 9 days ago

Small Language Models

Collection

All under 7B 🐁 • 84 items • Updated 9 days ago • 40

upvoted 2 articles 9 days ago

view article

Article

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

• 

10 days ago

•

38

view article

Article

Introducing Storage Buckets on the Hugging Face Hub

• 
• 
• +10

10 days ago

•

182

upvoted a changelog 9 days ago

view changelog

Hugging Face Changelog

Introducing Buckets: S3-like storage on the Hub

10 days ago

• 176

updated a collection 29 days ago

AMD Ryzen AI Max+ 395 Strix Halo

Collection

Quantized models benchmarked with Windows ROCm llama.cpp builds from Lemonade using recommended parameters. OpenCode testing done in WSL. • 10 items • Updated 18 days ago • 5

liked a model 29 days ago

unsloth/GLM-4.7-Flash-GGUF

Text Generation • 30B • Updated Feb 12 • 337k • 568

updated a collection 29 days ago

AMD Ryzen AI Max+ 395 Strix Halo

Collection

Quantized models benchmarked with Windows ROCm llama.cpp builds from Lemonade using recommended parameters. OpenCode testing done in WSL. • 10 items • Updated 18 days ago • 5

updated a collection 30 days ago

AMD Ryzen AI Max+ 395 Strix Halo

Collection

Quantized models benchmarked with Windows ROCm llama.cpp builds from Lemonade using recommended parameters. OpenCode testing done in WSL. • 10 items • Updated 18 days ago • 5

liked a model 30 days ago

ggml-org/gpt-oss-120b-GGUF

117B • Updated Oct 30, 2025 • 360k • 67

updated a collection 30 days ago

AMD Ryzen AI Max+ 395 Strix Halo

Collection

Quantized models benchmarked with Windows ROCm llama.cpp builds from Lemonade using recommended parameters. OpenCode testing done in WSL. • 10 items • Updated 18 days ago • 5

liked a model 30 days ago

unsloth/LFM2.5-1.2B-Instruct-GGUF

Text Generation • 1B • Updated Jan 6 • 3.78k • 31

upvoted a collection 30 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 23 days ago • 132

updated a collection about 1 month ago

Small Language Models

Collection

All under 7B 🐁 • 84 items • Updated 9 days ago • 40

liked 2 models about 1 month ago

Nanbeige/Nanbeige4.1-3B

Text Generation • 4B • Updated 22 days ago • 740k • • 1.01k

ACE-Step/Ace-Step1.5

Text-to-Audio • Updated Feb 3 • 33k • 650