Aj | LLM-salad

aj9o9

·

AI & ML interests

Obsessed with LLMs and ways to improve them! Super obsessed with with quants now, making them more efficient. https://x.com/ItsmeAjayKV

Recent Activity

new activity 1 day ago

aj9o9/Qwen3.8-27B-DSpine-b16-GGUF:Intel Arc Pro B65 (SYCL): measured numbers - n-max 15 is best for code/tool calls (5.5-5.9x), 3 for prose

new activity 2 days ago

aj9o9/Qwen3.8-27B-DSpine-b16-GGUF:Results on AMD (Radeon AI PRO R9700, ROCm/HIP): it works, code about 2x faster, images and prose not

updated a model 2 days ago

aj9o9/Qwen3.8-27B-DSpine-b16-GGUF

View all activity

Organizations

None yet

aj9o9 's models 9

aj9o9/Qwen3.8-27B-DSpine-b16-GGUF

Text Generation • 2B • Updated 1 day ago • 10.6k • 38

aj9o9/Qwen3.8-27B-Escha-W2-GGUF

Text Generation • 6B • Updated Sep 11 • 1.49k • 32

aj9o9/MiniCPM5-2B-DSpark-GGUF

Text Generation • 0.3B • Updated Sep 7 • 350 • 6

aj9o9/K2-Horizon-MoVA-36B-A4B-GGUF

Text Generation • 37B • Updated Sep 4 • 100 • 1

aj9o9/GLM-5.3-Flash-GGUF

Text Generation • 313B • Updated Sep 1 • 5.25k • 26

aj9o9/Qwen3.8-27B-GGUF

Text Generation • 27B • Updated Aug 17 • 101 • 2

aj9o9/Qwen3.6-35B-A3B-Escha-W2-GGUF

Text Generation • 7B • Updated Aug 13 • 191 • 9

aj9o9/nvidia-nemotron-3.5-lightning-30b

Text Generation • 33B • Updated Aug 12 • 179 • 2

aj9o9/Ling-3.0-flash-GGUF

Text Generation • 124B • Updated Aug 9 • 254 • 5