Skip to content

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

NameLast commit date
..
gpt-oss-merge
language_models
non_peft
text_to_speech_models
vision_models
run_offline_gguf_integration.py
test_compressed_export_schemes.py
test_export_api_surface.py
test_export_dispatch.py
test_fix_sentencepiece_gguf_robustness.py
test_fix_sentencepiece_tokenizer_guard.py
test_gguf_converter_remote_code.py
test_gguf_disk_preflight.py
test_gguf_export_and_inference.py
test_gguf_intermediate_on_destination.py
test_gguf_notebook_remote_code_guard.py
test_gguf_single_pass_export.py
test_imatrix_export.py
test_is_gpt_oss_detection.py
test_is_vlm_detection.py
test_lfm3_audio_gguf_config.py
test_llm_compressor_install_consent.py
test_llm_compressor_install_pin.py
test_llm_compressor_reinstall_guard.py
test_modelscope_repo_id.py
test_normalize_tied_weights_keys.py
test_offline_gguf_real_cache_integration.py
test_offline_gguf_vlm_tokenizer_7481.py
test_ollama_modelfile_trained_template.py
test_openvino_export.py
test_patch_saving_none_tokenizer.py
test_peft_base_export_guard.py
test_preserve_tokenizer_eos_token.py
test_prewarm_base_model_hub_cache.py
test_push_to_hub_gguf_single_commit.py
test_push_to_hub_lora_gguf_revision.py
test_qat_torchao_save.py
test_quant_method_none_normalization.py
test_qwen3_5_vlm_full_finetune_key_remap.py
test_restore_bytelevel_tokenizer_class.py
test_restore_source_tokenizer_class.py
test_save_clears_runtime_truncation.py
test_save_method_lora_routing.py
test_save_shell_injection.py
test_save_subprocess_utf8_encoding.py
test_tokenizer_class_export_finalization.py
test_torchao_remote_code_consent.py
test_unsloth_save.py