Add chip-specific model: models/gemma-4-E2B-it-tensor-g5.litertlm f35fb6e verified Chazzo2008 commited on Jun 12
Add chip-specific model: models/gemma-4-E2B-it-qualcomm-qcs8275.litertlm e8fdaed verified Chazzo2008 commited on Jun 12
Add chip-specific model: models/gemma-4-E2B-it-qualcomm-sm8750.litertlm 60c3792 verified Chazzo2008 commited on Jun 12
Add embed_tokens_q4f16.onnx_data (Chatterbox Turbo q4f16) a60dfc0 verified Chazzo2008 commited on Jun 2
Add conditional_decoder_q4f16.onnx_data (Chatterbox Turbo q4f16) 7e772cf verified Chazzo2008 commited on Jun 2
Add language_model_q4f16.onnx_data (Chatterbox Turbo q4f16) 0de18b4 verified Chazzo2008 commited on Jun 2
Add speech_encoder_q4f16.onnx_data (Chatterbox Turbo q4f16) 26fac66 verified Chazzo2008 commited on Jun 2
Add Qwen 3.5 2B multimodal LiteRT model (trevon/Qwen3.5-2B-LiteRT) 5eb8dc9 verified Chazzo2008 commited on May 11
Kokoro: switch to model_quantized.onnx (fixes ConvInteger/{0} crash in q8f16) 939c90b verified Chazzo2008 commited on Apr 24
Update: Gemma 3 1B INT4, Gemma 4 E2B + abliterated .litertlm, Kokoro v1.0 22945f8 verified Chazzo2008 commited on Apr 23
Update: Gemma 3 1B INT4, Gemma 4 E2B + abliterated .litertlm, Kokoro v1.0 ba68a8f verified Chazzo2008 commited on Apr 23
Chazzo2008 commited on 