deepseek-ai/deepseek-coder-6.7b-instruct
20 derivatives checked
- chatdb/natural-sql-7b: Full fine-tune
- TheBloke/deepseek-coder-6.7B-instruct-GGUF: Quantization
- mradermacher/deepseek-coder-6.7b-instruct-i1-GGUF: Quantization
- mradermacher/deepseek-coder-6.7b-instruct-GGUF: Same weights, converted
- second-state/Deepseek-Coder-6.7B-Instruct-GGUF: Quantization
- louisbrulenaudet/DevPearl-7B-dare-ties: Full fine-tune
- QuantFactory/deepseek-coder-6.7b-instruct-GGUF: Quantization
- Dzluck/deepseek-coder-6.7B-instruct-GGUF: Quantization
- QuantFactory/natural-sql-7b-GGUF: Full fine-tune
- godolike/deepseek-coder-6.7b-instruct-Q4_K_M-GGUF: Quantization
- TheBloke/deepseek-coder-6.7B-instruct-AWQ: Quantization
- chatdb/natural-sql-7b-GGUF: Full fine-tune
- TheBloke/deepseek-coder-6.7B-instruct-GPTQ: Quantization
- DavidBPunkt/deepseek-coder-6.7B-instruct-GGUF: Quantization
- tensorblock/deepseek-coder-6.7b-instruct-GGUF: Quantization
- liodon-ai/deepseek-coder-6.7b-instruct-FP8: Quantization
- xanyun/deepseek-coder-6.7b-instruct-Q4_K_M-GGUF: Quantization
- raihan-js/orch-7b: Quantization
- cfahlgren1/NaturalSQL-6.7B-v0: Full fine-tune
- louisbrulenaudet/DevPearl-2x7B: MoE built from dense models
6 other repos hold byte-for-byte identical weight files.