Anjey Sapkovski

anjeysapkovski's activity

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

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B 4 days ago

ThinkingCap-Qwen3.6-35b-a3b ?

❤️ 5

7

#6 opened about 1 month ago by

Narutoouz

liked a model 16 days ago

ai-sage/GigaAM-Multilingual

Automatic Speech Recognition • Updated 24 days ago • 11k • 74

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B 17 days ago

MTP version request

❤️🔥 3

2

#20 opened 17 days ago by

anjeysapkovski

liked a dataset 2 months ago

eaddario/imatrix-calibration

Viewer • Updated May 5 • 299 • 13.4k • 56

liked a model 2 months ago

DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF

Image-Text-to-Text • 27B • Updated 21 days ago • 92.2k • 423

New activity in Jackrong/Qwopus3.6-35B-A3B-v1-MTP-GGUF 2 months ago

Request for UD quants of the model

🚀 1

#2 opened 2 months ago by

anjeysapkovski

liked a model 2 months ago

Jackrong/Qwopus3.6-35B-A3B-v1-MTP-GGUF

Image-Text-to-Text • 0.4B • Updated 29 days ago • 4.98k • 56

New activity in byteshape/Qwen3.6-35B-A3B-MTP-GGUF 2 months ago

Same speed on 5060 Ti as llamacpp MTP model

➕ 1

#5 opened 2 months ago by

anjeysapkovski

liked a model 3 months ago

NemoStation/Marlin-2B

Video-Text-to-Text • 2B • Updated May 30 • 6.73k • 575

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 3 months ago

Starts with 50% speedup, but speed very fast decreases

2

#21 opened 3 months ago by

seleznyov

New activity in z-lab/Qwen3.6-35B-A3B-DFlash 3 months ago

draft with llama.cpp?

👀 2

3

#2 opened 4 months ago by

Schnabulator

New activity in Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF 3 months ago

Thank you!!

🤗 3

2

#4 opened 3 months ago by

zrfior

liked 3 models 3 months ago

lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled

Text Generation • 36B • Updated Apr 23 • 7.25k • • 200

amazeble/Qwen3.6-35B-REAP-Pruned-ratio-0.3-Q4_K_M-GGUF

Text Generation • 25B • Updated May 1 • 76 • 2

keithnull/Qwen3.6-35B-A3B-REAM-192

Image-Text-to-Text • 27B • Updated May 8 • 28 • 6

reacted to DavidAU's post with ❤️ 3 months ago

view post

Post

8911

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

• 
• 
• 
• 10 replies

·

❤️

11

11

😎

2

2

🚀

1

1

+

Reply

liked 4 models 3 months ago

DavidAU/Qwen3.6-27B-NEO-CODE-Di-IMatrix-MAX-GGUF

Image-Text-to-Text • 27B • Updated 21 days ago • 4.33k • 73

prism-ml/Ternary-Bonsai-8B-gguf

Text Generation • 8B • Updated Jun 10 • 128k • 132

openai/privacy-filter

Token Classification • 1B • Updated Apr 22 • 525k • • 1.72k

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16

Text Generation • 27B • Updated 22 days ago • 11.7k • • 144