What are the hardware requirements for DeepSeek V4 Flash DSpark?

DeepSeek V4 Flash DSpark requires approximately 152.3 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 DSpark and how large is it?

DeepSeek V4 Flash DSpark is developed by deepseek-ai, a model with 165.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does DeepSeek V4 Flash DSpark perform on standard benchmarks?

DeepSeek V4 Flash DSpark has the following published scores: LMSYS ELO 1438. Compare against reference models on this page or on the LLM Explorer leaderboards.

DeepSeek V4 Flash DSpark by deepseek-ai — VRAM 152.3GB, 1024K context

Name: DeepSeek V4 Flash DSpark
Author: deepseek-ai

DeepSeek V4 Flash DSpark is an open-source language model by deepseek-ai. Features: 165.3b LLM, VRAM: 152.3GB, Context: 1024K, License: mit, LLM Explorer Score: 0.55, ELO: 1438.

Arxiv:2606.19348 8-bit Deepseek v4 Endpoints compatible Fp8 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-DSpark

DeepSeek V4 Flash DSpark Benchmarks

LMSys ELO 1438 vs 1272 (so35) 13.1%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

DeepSeek V4 Flash DSpark Parameters and Internals

LLM Name	DeepSeek V4 Flash DSpark
Repository 🤗	https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-DSpark
Model Size	165.3b
Required VRAM	152.3 GB
Updated	2026-07-14
Maintainer	deepseek-ai
Model Type	deepseek_v4
Model Files	1.1 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 3.6 GB: 42-of-48 3.6 GB: 43-of-48
Model Architecture	DeepseekV4ForCausalLM
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	4.57.1
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the DeepSeek V4 Flash DSpark 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 DSpark

Best Alternatives	Context / RAM	Downloads	Likes
... DSpark Abliterated Uncensored	1024K / 134.3 GB	13168	14