John Gil Cubas

JohnRoger's activity

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

liked a model about 6 hours ago

huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated

Any-to-Any • 27B • Updated 1 day ago • 162 • 14

upvoted a collection about 6 hours ago

gemma-4-abliterated

Collection

6 items • Updated 1 day ago • 7

liked 2 models about 8 hours ago

Jiunsong/supergemma4-26b-abliterated-multimodal

Image-Text-to-Text • 26B • Updated about 6 hours ago • 7

Jiunsong/supergemma4-26b-abliterated-multimodal-gguf-4bit

Image-Text-to-Text • 25B • Updated about 6 hours ago • 1

liked a model about 16 hours ago

arcee-ai/Trinity-Mini-GGUF

Text Generation • 26B • Updated Dec 18, 2025 • 1.61k • 55

liked a model about 17 hours ago

arcee-ai/Trinity-Mini

Text Generation • Updated Dec 11, 2025 • 7.34k • 188

upvoted a collection about 18 hours ago

Granite 4.0 Nano Language Models

Collection

Ultra-compact language models designed for the edge and on-device deployment. • 9 items • Updated 11 days ago • 100

liked 2 models 2 days ago

nvidia/Nemotron-Terminal-32B

Text Generation • 33B • Updated Feb 27 • 4.22k • 37

nvidia/Nemotron-Cascade-2-30B-A3B

Text Generation • 32B • Updated 3 days ago • 280k • 472

upvoted a collection 2 days ago

NVIDIA EGM

Collection

Efficient Grounding Models • 4 items • Updated 6 days ago • 6

liked 2 models 3 days ago

mradermacher/Marco-Mini-Instruct-GGUF

17B • Updated 3 days ago • 4.17k • 3

AIDC-AI/Marco-Mini-Instruct

Text Generation • 17B • Updated 3 days ago • 674 • 30

upvoted a collection 3 days ago

Marco-MoE

Collection

A suit of multilingual MoE models with highly-sparse architectures • 5 items • Updated 5 days ago • 13

reactedto DavidAU's post with ❤️ 3 days ago

view post

Post

3110

Going NUCLEAR: Gemma 4 E4B uncensored, and tuned exceeds Gemma 4 26B-A4B in critical benchmarks.

De-censored, tuned, and tuned again via Unsloth using custom in house datasets and methods:

DavidAU/gemma-4-E4B-it-The-DECKARD-Expresso-Universe-HERETIC-UNCENSORED-Thinking

See translation

• 
• 
• 
• 4 replies

·

❤️

8

8

😎

2

2

🚀

1

1

+

Reply

liked a model 3 days ago

DevQuasar/ByteDance-Seed.Stable-DiffCoder-8B-Instruct-GGUF

Text Generation • 8B • Updated Jan 27 • 146 • 3

upvoted a collection 3 days ago

Ling 2.5

Collection

The newest flagship non-reasoning model series. • 1 item • Updated 10 days ago • 11

liked a model 3 days ago

ByteDance-Seed/Stable-DiffCoder-8B-Instruct

Text Generation • 8B • Updated 18 days ago • 907 • 132

upvoted a collection 3 days ago

Stable-DiffCoder

Collection

2 items • Updated Jan 22 • 6

liked a model 3 days ago

zed-industries/zeta-2

Text Generation • 8B • Updated 20 days ago • 1.82k • 126

upvoted a collection 3 days ago

Bonsai requantized

Collection

requantized Bonsai for software that doesn't support Q1_0_g128 quantization. • 3 items • Updated 10 days ago • 2