unsloth/DeepSeek-V4-Flash-0731-GGUF
Not comparable yet vs deepseek-ai/DeepSeek-V4-Flash-0731. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (7 of 72317/81 match), usually an architecture llama.cpp's name map doesn't cover yet.
3 derivatives checked
- meshllm/DeepSeek-V4-Flash-0731-UD-Q4_K_XL-layers: Full fine-tune (fewer layers)
- ioworker0/DeepSeek-V4-Flash-0731-REAP: Full fine-tune (fewer layers)
- Lynxpda/DeepSeek-V4-Flash-0731-DSpark-Drafter-Q2_K_S-GGUF: Quantization