FOXAI SEARCH
Search FoxAI
AI Models 85012
- refined-web-model-test↗
explosion-testing
- mms-tts-hlt↗
facebook
- mms-tts-jam↗
facebook
- omniASR-W2V-300M↗
facebook
- doctr-dummy-torch-mobilenet-v3-large↗
Felix92
- Darwin-27B-RSI↗
FINAL-Bench
- panorama-qwen-image-lora↗
furaidosu
- t5gemma-b-b-prefixlm-it↗
Google
- bekko-embedding-v1-a8m↗
hotchpotch
bekko-embedding-v1-a8m is an ultra-compact multilingual text embedding model. It has just 8M active parameters — light enough to run comfortably even on low-spec CPUs — yet its retrieval quality is comparable to models with 3–10x more active parameters. You can also try bekko right in your browser: the bekko-embedding-web demo runs the model fully client-side with Transformers.js — no server involved. > [!NOTE] > For a guided overview of the models, training recipe, and results, read Bekko Embedding: how small can a multilingual retrieval model be?.
- DeepSeek-R1-Distill-Llama-8B-abliterated-Q8_0-GGUF↗
Human23
