llm-jp/llm-jp-4-8b-thinking
12 derivatives checked
- ikedachin/llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v3: LoRA-style
- ikedachin/llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v4: LoRA-style
- ikedachin/llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v2: LoRA-style
- llm-jp/llm-jp-4-vl-9b: Full fine-tune (fewer layers)
- ikedachin/llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v1: LoRA-style
- mlx-community/llm-jp-4-8b-thinking-4bit: Quantization
- mmnga-o/llm-jp-4-8b-thinking-gguf: Quantization
- masahiroid/llm-jp-4-8b-thinking-4bit-mlx: Quantization
- alfredplpl/llm-jp-4-8b-thinking-gguf: Same weights, converted
- ikedachin/llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v4_1: LoRA-style
- mlx-community/llm-jp-4-8b-thinking-8bit: Quantization
- tokinasin/llm-jp-4-8b-thinking-uncensored-ara: Abliterated