Jerry Mars

deucebucket's activity

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

New activity in deucebucket/Qwen3.6-35B-A3B-Cerebellum-GGUF about 2 hours ago

The first adjusted model I've used that actually seems to be equal-or-better to previous alternatives

2

#2 opened about 7 hours ago by

Tribbler

New activity in google/gemma-4-26B-A4B-it 4 days ago

GGUF available — Cerebellum v3 (11 GB, ablation-guided mixed-precision)

2

#37 opened 13 days ago by

deucebucket

New activity in deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF 4 days ago

What about uncensored/abliterated version?

❤️ 1

1

#2 opened 4 days ago by

tima2431

New activity in deucebucket/Qwen3.6-35B-A3B-Cerebellum-GGUF 8 days ago

Qwen 3.6 35B-A3B Cerebellum — 12 GB, fits 16 GB VRAM

2

#1 opened 11 days ago by

deucebucket

New activity in deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF 11 days ago

Gemma-4-E4B-it-Cerebellum-v1

2

#1 opened 12 days ago by

dont-remember-it

New activity in deucebucket/Qwen36-27B-Cerebellum-v4-Demo 12 days ago

Apply for a GPU community grant: Personal project

#1 opened 12 days ago by

deucebucket

New activity in Qwen/Qwen3.6-27B 13 days ago

GGUF available — Cerebellum v4 (ablation-guided mixed-precision)

👍 2

#28 opened 13 days ago by

deucebucket

New activity in google/gemma-4-E4B-it 13 days ago

GGUF available — Cerebellum v1 & v2 (ablation-guided mixed-precision)

#29 opened 13 days ago by

deucebucket

New activity in nvidia/Gemma-4-26B-A4B-NVFP4 13 days ago

GGUF available — Cerebellum v3 (11 GB, ablation-guided mixed-precision)

#1 opened 13 days ago by

deucebucket

New activity in deucebucket/vadugwi-paper about 1 month ago

[bot] Conversion to Parquet

#1 opened about 1 month ago by

parquet-converter