What are the hardware requirements for DeepSeek V4 Flash Vision Exp?

DeepSeek V4 Flash Vision Exp requires approximately 146 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepSeek V4 Flash Vision Exp and how large is it?

DeepSeek V4 Flash Vision Exp is developed by unsloth, a model with 304.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate DeepSeek V4 Flash Vision Exp?

DeepSeek V4 Flash Vision Exp is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepSeek V4 Flash Vision Exp by unsloth — VRAM 146GB, 1024K context

Name: DeepSeek V4 Flash Vision Exp
Author: unsloth

DeepSeek V4 Flash Vision Exp is an open-source language model by unsloth. Features: 304.6b LLM, VRAM: 146GB, Context: 1024K, License: mit, LLM Explorer Score: 0.28.

8-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Conversational Deepseek v4 Endpoints compatible Fp8 Region:us Safetensors Sharded Tensorflow Unsloth Vision

Model Card on HF 🤗: https://huggingface.co/unsloth/DeepSeek-V4-Flash-Vision-Exp

DeepSeek V4 Flash Vision Exp Parameters and Internals

LLM Name	DeepSeek V4 Flash Vision Exp
Repository 🤗	https://huggingface.co/unsloth/DeepSeek-V4-Flash-Vision-Exp
Base Model(s)	DeepSeek V4 Flash Vision Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Model Size	304.6b
Required VRAM	146 GB
Updated	2026-09-04
Maintainer	unsloth
Model Type	deepseek_v4
Model Files	2.0 GB: 1-of-48 3.6 GB: 2-of-48 3.6 GB: 3-of-48 3.6 GB: 4-of-48 3.6 GB: 5-of-48 3.6 GB: 6-of-48 3.6 GB: 7-of-48 3.6 GB: 8-of-48 3.6 GB: 9-of-48 3.6 GB: 10-of-48 3.6 GB: 11-of-48 3.6 GB: 12-of-48 3.6 GB: 13-of-48 3.6 GB: 14-of-48 3.6 GB: 15-of-48 3.6 GB: 16-of-48 3.6 GB: 17-of-48 3.6 GB: 18-of-48 3.6 GB: 19-of-48 3.6 GB: 20-of-48 3.6 GB: 21-of-48 3.6 GB: 22-of-48 3.6 GB: 23-of-48 3.6 GB: 24-of-48 3.6 GB: 25-of-48 3.6 GB: 26-of-48 3.6 GB: 27-of-48 3.6 GB: 28-of-48 3.6 GB: 29-of-48 3.6 GB: 30-of-48 3.6 GB: 31-of-48 3.6 GB: 32-of-48 3.6 GB: 33-of-48 3.6 GB: 34-of-48 3.6 GB: 35-of-48 3.6 GB: 36-of-48 3.6 GB: 37-of-48 3.6 GB: 38-of-48 3.6 GB: 39-of-48 3.6 GB: 40-of-48 3.6 GB: 41-of-48
Model Architecture	DeepseekV4ForCausalLM
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.16.0.dev0
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the DeepSeek V4 Flash Vision Exp capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the DeepSeek V4 Flash Vision Exp

Model	Likes	Downloads	VRAM
...V4 Flash Vision Exp AWQ DSpark	1	565	136 GB

Best Alternatives to DeepSeek V4 Flash Vision Exp

Best Alternatives	Context / RAM	Downloads	Likes
DeepSeek V4 Flash Vision Exp	1024K / 146 GB	17893	441
...Seek V4 Flash Vision Exp NVFP4	1024K / 116 GB	1601	1
... Flash Vision Exp MXFP4 DSpark	1024K / 142.4 GB	1051	1
...ash Vision Exp Mlx OQ4e DSpark	1024K / 166 GB	323	1
...ash Vision Exp Mlx OQ8e DSpark	1024K / 166.1 GB	220	1
...eek V4 Flash 0731 Vision NVFP4	1024K / 111.3 GB	238	15
...Seek V4 Flash Vision Exp NVFP4	1024K / 119.8 GB	146	1
...h Vision Exp Abliterated NVFP4	1024K / 123.6 GB	72	1
...Seek V4 Flash 0731 Vision BF16	1024K / 116.3 GB	78	3

Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepSeek-V4-Flash-Vision-Exp.