What are the hardware requirements for DeepSeek V4 Flash Vision Exp NVFP4?

DeepSeek V4 Flash Vision Exp NVFP4 requires approximately 116 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 NVFP4 and how large is it?

DeepSeek V4 Flash Vision Exp NVFP4 is developed by Solstice-AI, 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 NVFP4?

DeepSeek V4 Flash Vision Exp NVFP4 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 NVFP4 by Solstice-AI — VRAM 116GB, 1024K context

Name: DeepSeek V4 Flash Vision Exp NVFP4
Author: Solstice-AI

DeepSeek V4 Flash Vision Exp NVFP4 is an open-source language model by Solstice-AI. Features: 304.6b LLM, VRAM: 116GB, Context: 1024K, License: mit, LLM Explorer Score: 0.34.

8-bit B200 Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Blackwell Deepseek-v4 Deepseek v4 Dgx-spark Fp4 Fp8 Gguf Image-text-to-text Model optimizer Modelopt Multimodal Nvfp4 Quantized Region:us Safetensors Sharded Solstice-ai Tensorflow Tensorrt-llm Vision Vllm

Model Card on HF 🤗: https://huggingface.co/Solstice-AI/DeepSeek-V4-Flash-Vision-Exp-NVFP4

DeepSeek V4 Flash Vision Exp NVFP4 Parameters and Internals

LLM Name	DeepSeek V4 Flash Vision Exp NVFP4
Repository 🤗	https://huggingface.co/Solstice-AI/DeepSeek-V4-Flash-Vision-Exp-NVFP4
Base Model(s)	DeepSeek V4 Flash Vision Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Model Size	304.6b
Required VRAM	116 GB
Updated	2026-09-10
Maintainer	Solstice-AI
Model Type	deepseek_v4
Model Files	2.0 GB: 1-of-48 3.8 GB: 2-of-48 3.8 GB: 3-of-48 3.8 GB: 4-of-48 3.8 GB: 5-of-48 3.8 GB: 6-of-48 3.8 GB: 7-of-48 3.8 GB: 8-of-48 3.8 GB: 9-of-48 3.8 GB: 10-of-48 3.8 GB: 11-of-48 3.8 GB: 12-of-48 3.8 GB: 13-of-48 3.8 GB: 14-of-48 3.8 GB: 15-of-48 3.8 GB: 16-of-48 3.8 GB: 17-of-48 3.8 GB: 18-of-48 3.8 GB: 19-of-48 3.8 GB: 20-of-48 3.8 GB: 21-of-48 3.8 GB: 22-of-48 3.8 GB: 23-of-48 3.8 GB: 24-of-48 3.8 GB: 25-of-48 3.8 GB: 26-of-48 3.8 GB: 27-of-48 3.8 GB: 28-of-48 3.8 GB: 29-of-48 3.8 GB: 30-of-48 3.8 GB: 31-of-48
Model Architecture	DeepseekV4ForCausalLM
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.0.0
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the DeepSeek V4 Flash Vision Exp NVFP4 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

Best Alternatives to DeepSeek V4 Flash Vision Exp NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
DeepSeek V4 Flash Vision Exp	1024K / 146 GB	17893	441
... Flash Vision Exp MXFP4 DSpark	1024K / 142.4 GB	1051	1
DeepSeek V4 Flash Vision Exp	1024K / 146 GB	487	8
...ash Vision Exp Mlx OQ4e DSpark	1024K / 166 GB	323	1
...ash Vision Exp Mlx OQ8e DSpark	1024K / 166.1 GB	220	1
...Seek V4 Flash Vision Exp NVFP4	1024K / 119.8 GB	146	1
...eek V4 Flash 0731 Vision NVFP4	1024K / 111.3 GB	238	15
...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 Solstice-AI/DeepSeek-V4-Flash-Vision-Exp-NVFP4.