IQuest-Coder-V1-7B-Thinking-GGUF

GGUF quant collection for IQuestLab/IQuest-Coder-V1-7B-Thinking.

Included quants

• IQuest-Coder-V1-7B-Thinking-Q4_K_M.gguf
• IQuest-Coder-V1-7B-Thinking-Q6_K.gguf
• IQuest-Coder-V1-7B-Thinking-Q8_0.gguf

Checksums

• 4a7f9a129a27b5bedcf2946453375c51cf8d3ed09b76868cfe524832d0ac8738 IQuest-Coder-V1-7B-Thinking-Q4_K_M.gguf
• 8caab18bb8526afe5180f6bcb99ce903d92ae0da173d5443d019374ad6215ab0 IQuest-Coder-V1-7B-Thinking-Q6_K.gguf
• c9a16029ef9d8b7ac3d2ad26691456cedb45eafcce8f5d0c738438cc51f4dd13 IQuest-Coder-V1-7B-Thinking-Q8_0.gguf

Provenance

• Source model: https://huggingface.co/IQuestLab/IQuest-Coder-V1-7B-Thinking
• Converted + quantized with llama.cpp (convert_hf_to_gguf.py + llama-quantize).
• Metadata hygiene scan passed for local/personal identifiers before upload.

License

This repo redistributes quantized weights from IQuestLab/IQuest-Coder-V1-7B-Thinking and includes the upstream LICENSE file verbatim. Please follow upstream license terms, including the IQuest commercial UI attribution requirement.