Henry Kroll III
hellork
AI & ML interests
Small, open-source LLMs for mobile with <= 4Gb graphics, text generation, image manipulation recognition, 3D model generation, language preservation and translation, and business use cases.
Organizations
LLAVA Vision Models
Models to query photos
-
xtuner/llava-phi-3-mini-gguf
Image-to-Text • 4B • Updated • 1.66k • 132 -
cjpais/llava-1.6-mistral-7b-gguf
Image-Text-to-Text • 7B • Updated • 5.11k • 106 -
xtuner/llava-llama-3-8b-v1_1-gguf
Image-to-Text • 8B • Updated • 3.3k • 215 -
second-state/Llava-v1.5-7B-GGUF
Text Generation • 0.3B • Updated • 2.63k • 11
Under 10b iq4_nl gguf
Under 10B GGUFs Non-linear Quantized to try on 4GiB VRAM. Leaderboard https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
Text-to-video
text-to-image <=8B gguf
LLAVA Vision Models
Models to query photos
-
xtuner/llava-phi-3-mini-gguf
Image-to-Text • 4B • Updated • 1.66k • 132 -
cjpais/llava-1.6-mistral-7b-gguf
Image-Text-to-Text • 7B • Updated • 5.11k • 106 -
xtuner/llava-llama-3-8b-v1_1-gguf
Image-to-Text • 8B • Updated • 3.3k • 215 -
second-state/Llava-v1.5-7B-GGUF
Text Generation • 0.3B • Updated • 2.63k • 11
Under 10b iq4_xs gguf
Under 10b iq4_nl gguf
Under 10B GGUFs Non-linear Quantized to try on 4GiB VRAM. Leaderboard https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard