Skip to content

rdtand

DeepSeek-V4-Flash-0731-PrismaQuant-AQUA-gridbook-87GB-spark-vllm

rdtand/DeepSeek-V4-Flash-0731-PrismaQuant-AQUA-gridbook-87GB-spark-vllm

DeepSeek-V4-Flash-0731-PrismaQuant-AQUA-gridbook-87GB-spark-vllm is a machine learning model from rdtand. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for vllm. The card lists the license as mit.

A mixed-precision, per-Linear quantization of deepseek-ai/DeepSeek-V4-Flash-0731 (284B-A38B, 43 layers, 256 routed + 1 shared expert, FP8-native source) that fits the full model body in 87.08 GB — sized for a single 1…

Downloads · 30 days

73

10% of all-time downloads

All-time downloads

729

Public

Parameters

85.4B

87.2 GB on disk

Likes

4

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors87.1 GB · 100%

Parameter types

How the weights are stored.

U881.7B · 96%

Base models

Library
vllm
Type
deepseek_v4
License
mit
Created
Aug 18, 2026
Updated
Aug 21, 2026