fraQtl AI Research

company

https://fraQtl.ai

AI & ML interests

KV cache compression, inference optimization, model compression

Recent Activity

Zenalyze updated a model about 4 hours ago

fraQtl/Qwen3.6-35B-A3B-fraQtl-kv

Zenalyze updated a Space about 17 hours ago

Zenalyze published a Space about 17 hours ago

View all activity

updated a model about 4 hours ago

fraQtl/Qwen3.6-35B-A3B-fraQtl-kv

Updated about 4 hours ago

updated a Space about 17 hours ago

README

published a Space about 17 hours ago

README

updated a model about 18 hours ago

fraQtl/Mistral-7B-fraqtl

7B • Updated about 18 hours ago • 86

published a model about 18 hours ago

fraQtl/Qwen3.6-35B-A3B-fraQtl-kv

Updated about 4 hours ago

published a Space about 22 hours ago

fraQtl — Compressed LLM Demo

Generate text and test retrieval with a compressed Mistral‑7B

updated a model 1 day ago

fraQtl/Mistral-7B-compressed

Updated about 16 hours ago • 98

published a model 1 day ago

fraQtl/Mistral-7B-compressed

Updated about 16 hours ago • 98

updated a Space 1 day ago

fraQtl — Compressed LLM Demo

Generate text and test retrieval with a compressed Mistral‑7B

updated 3 models 3 days ago

fraQtl/TinyLlama-1.1B-optimized

1B • Updated 3 days ago • 48

fraQtl/Qwen-2.5-3B-optimized

3B • Updated 3 days ago • 37

fraQtl/Llama-3.2-3B-optimized

3B • Updated 3 days ago • 42

published a model 3 days ago

fraQtl/Mistral-7B-fraqtl

7B • Updated about 18 hours ago • 86

published 3 models 7 days ago

fraQtl/Qwen-2.5-3B-optimized

3B • Updated 3 days ago • 37

fraQtl/Llama-3.2-3B-optimized

3B • Updated 3 days ago • 42

fraQtl/TinyLlama-1.1B-optimized

1B • Updated 3 days ago • 48