Skip to content

anoane

DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw

anoane/DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw

DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw is a text generation model from anoane. Use it when you need the model to write or continue text. It is set up for exllamav3. The card lists the license as mit.

An exl3 quantization of DeepSeek-V4-Flash-0731 in which every routed expert carries its own bit-width. 11,008 experts are individually assigned a 2-, 3- or 4-bit trellis code according to how much each one is actually…

Downloads · 30 days

45

4% of all-time downloads

All-time downloads

1K

Public

Parameters

52.2B

110 GB on disk

Likes

3

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors110 GB · 100%

Parameter types

How the weights are stored.

I1651.3B · 98%

Try a prompt

Base models

Task
Text Generation
Library
exllamav3
Type
deepseek_v4
License
mit
Created
Aug 22, 2026
Updated
Aug 24, 2026