unsloth/DeepSeek-V4-Flash-GGUF
Not comparable yet vs deepseek-ai/DeepSeek-V4-Flash. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (88 of 69187/1328 match), usually an architecture llama.cpp's name map doesn't cover yet.
1 derivatives checked
- meshllm/DeepSeek-V4-Flash-UD-Q4_K_XL-layers: Quantization (fewer layers)