ModelListadosExterno
DeepSeek V4 Flash GGUF
Using MTP requires am17an/llama.cpp:dsv4-mtp until llama.cpp#25784 is merged.
TipoOtherModelo basedeepseek-ai/DeepSeek-V4-FlashVersãoRevision 4810cf3Dnota
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 3,51–145 GB
- Modelo base
- deepseek-ai/DeepSeek-V4-Flash
- Versão
- vRevision 4810cf3
- Atualizado
- 4 de out. de 2026
- Downloads
- 3 mil
- Fonte
- Hugging Face
Descrição da fonte
GGUF quantizations of DeepSeek-V4-Flash.
Using MTP requires am17an/llama.cpp:dsv4-mtp until llama.cpp#25784 is merged.
Fontes
1 fonte
Fontes
1 fonteHugging FacePrimárioVersão 4810cf35923cf2798d97454b247f697815f4fb30
huggingface.co/ddh0/DeepSeek-V4-Flash-GGUF/tree/4810cf35923cf2798d97454b247f697815f4fb30Verificado 1 de set.
Artefatos de modelo
5 artefatos
Artefatos de modelo
5 artefatosTrechos de fonte
2 trechos
Trechos de fonte
2 trechos--- base_model: - deepseek-ai/DeepSeek-V4-Flash --- GGUF quantizations of DeepSeek-V4-Flash. Using MTP requires [am17an/llama.cpp:dsv4-mtp](https://github.com/am17an/llama.cpp/tree/dsv4-mtp) until [llama.cpp#25784](https://github.com/ggml-org/llama.cpp/pull/25784) is merged.
Source context: 2957 downloads · 7 likes · Repo ddh0/DeepSeek-V4-Flash-GGUF
