Azzzzz

Jahaz's activity

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

New activity in DreamFast/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark 10 days ago

Basically base on that analysis, Huihui is better than ton of finetunes in throughput

1

#4 opened 10 days ago by

Jahaz

New activity in moonshotai/Kimi-K2.6 about 1 month ago

This model introduces itself as Anthropic, if asked in Korean

12

#23 opened about 1 month ago by

picopress

New activity in shreyan35/Qwen3.6-35b-a3b-claude-opus-4.6-thinking-distil-s8-gguf about 1 month ago

Didn't try Qwen3.6 official, but this finetune outperforms Qwen3.6 35B in real world testing.

12

#2 opened about 2 months ago by

Jahaz

New activity in DavidAU/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B about 2 months ago

Compare with extent LFM 1b, reduce activated experts to 1b in larger models might be better?

#1 opened about 2 months ago by

Jahaz

New activity in Jahaz/multi-lora-llama-7b-ggml-q5-1 about 3 years ago

Excellent Model

9

#2 opened about 3 years ago by

PrimeD

Excellent Model

9

#2 opened about 3 years ago by

PrimeD

Excellent Model

9

#2 opened about 3 years ago by

PrimeD