Skip to content
ModelListedExternal
Download

DeepSeek V4 Flash GGUF

Using MTP requires am17an/llama.cpp:dsv4-mtp until llama.cpp#25784 is merged.

Sourcehuggingface.co/ddh0/DeepSeek-V4-Flash-GGUF/tree/4810cf35923cf2798d97454b247f697815f4fb30
KindOtherBase modeldeepseek-ai/DeepSeek-V4-FlashVersionRevision 4810cf3Dgrade

Model source

Kind
Other
File size
3.51–145 GB
Base model
deepseek-ai/DeepSeek-V4-Flash
Version
vRevision 4810cf3
Updated
Oct 4, 2026
Downloads
3K
Source
Hugging Face

Source description

GGUF quantizations of DeepSeek-V4-Flash.

Using MTP requires am17an/llama.cpp:dsv4-mtp until llama.cpp#25784 is merged.

Sources

1 source
Hugging FacePrimaryVersion 4810cf35923cf2798d97454b247f697815f4fb30
huggingface.co/ddh0/DeepSeek-V4-Flash-GGUF/tree/4810cf35923cf2798d97454b247f697815f4fb30

Verified Sep 1

Model artifacts

5 artifacts

DeepSeek-V4-Flash-3.86bpw-IQ3_S.gguf

gguf · 128 GB · SHA-256 46a1c2a740d8…c758 · Hugging Face

Download

DeepSeek-V4-Flash-3.86bpw-Q3_K.gguf

gguf · 128 GB · SHA-256 6a1bb6ab90d5…1b26 · Hugging Face

Download

DeepSeek-V4-Flash-MTP-3.93bpw.gguf

gguf · 3.51 GB · SHA-256 539e2e1fe0ac…a212 · Hugging Face

Download

DeepSeek-V4-Flash-MTP-4.93bpw.gguf

gguf · 4.41 GB · SHA-256 d428e3eb8443…3e74 · Hugging Face

Download

DeepSeek-V4-Flash-MXFP4.gguf

gguf · 145 GB · SHA-256 ba686121392f…197d · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 1huggingface.co/ddh0/DeepSeek-V4-Flash-GGUF

--- 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.

NoteSep 1huggingface.co/ddh0/DeepSeek-V4-Flash-GGUF

Source context: 2957 downloads · 7 likes · Repo ddh0/DeepSeek-V4-Flash-GGUF