What are the hardware requirements for DeepSeek V2.5 1210?

DeepSeek V2.5 1210 requires approximately 378.4 GB of VRAM and supports a context window of 160K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepSeek V2.5 1210 and how large is it?

DeepSeek V2.5 1210 is developed by deepseek-ai, a model with 235.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does DeepSeek V2.5 1210 perform on standard benchmarks?

DeepSeek V2.5 1210 has the following published scores: LMSYS ELO 1323. Compare against reference models on this page or on the LLM Explorer leaderboards.

DeepSeek V2.5 1210 by deepseek-ai — VRAM 378.4GB, 160K context

Name: DeepSeek V2.5 1210
Author: deepseek-ai

DeepSeek V2.5 1210 is an open-source language model by deepseek-ai. Features: 235.7b LLM, VRAM: 378.4GB, Context: 160K, License: other, LLM Explorer Score: 0.31, ELO: 1323.

Arxiv:2405.04434 Conversational Custom code Deepseek v2 Endpoints compatible Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210

DeepSeek V2.5 1210 Benchmarks

LMSys ELO 1323 vs 1272 (so35) 4%

^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 V2.5 1210 Parameters and Internals

LLM Name	DeepSeek V2.5 1210
Repository 🤗	https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210
Model Size	235.7b
Required VRAM	378.4 GB
Updated	2026-06-21
Maintainer	deepseek-ai
Model Type	deepseek_v2
Model Files	8.6 GB: 1-of-55 8.6 GB: 2-of-55 8.6 GB: 3-of-55 8.6 GB: 4-of-55 8.6 GB: 5-of-55 8.6 GB: 6-of-55 8.6 GB: 7-of-55 8.6 GB: 8-of-55 8.6 GB: 9-of-55 8.6 GB: 10-of-55 8.6 GB: 11-of-55 8.6 GB: 12-of-55 8.6 GB: 13-of-55 8.6 GB: 14-of-55 8.6 GB: 15-of-55 8.6 GB: 16-of-55 8.6 GB: 17-of-55 8.6 GB: 18-of-55 8.6 GB: 19-of-55 8.6 GB: 20-of-55 8.6 GB: 21-of-55 8.6 GB: 22-of-55 8.6 GB: 23-of-55 8.6 GB: 24-of-55 8.6 GB: 25-of-55 8.6 GB: 26-of-55 8.6 GB: 27-of-55 8.6 GB: 28-of-55 8.6 GB: 29-of-55 8.6 GB: 30-of-55 8.6 GB: 31-of-55 8.6 GB: 32-of-55 8.6 GB: 33-of-55 8.6 GB: 34-of-55 8.6 GB: 35-of-55 8.6 GB: 36-of-55 8.6 GB: 37-of-55 8.6 GB: 38-of-55 8.6 GB: 39-of-55 8.6 GB: 40-of-55 8.6 GB: 41-of-55 8.6 GB: 42-of-55 8.6 GB: 43-of-55 8.6 GB: 44-of-55
Model Architecture	DeepseekV2ForCausalLM
License	other
Context Length	163840
Model Max Length	163840
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<｜end▁of▁sentence｜>
Vocabulary Size	102400
Torch Data Type	bfloat16

Rank the DeepSeek V2.5 1210 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 V2.5 1210

Model	Likes	Downloads	VRAM
DeepSeek V2.5 1210 4bit	4	305	133 GB
DeepSeek V2.5 1210 3bit	2	36	102 GB

Best Alternatives to DeepSeek V2.5 1210

Best Alternatives	Context / RAM	Downloads	Likes
DeepSeek V2.5	160K / 378.4 GB	3451	734
DeepSeek V2	160K / 378.4 GB	9698	334
DeepSeek Coder V2 Instruct	160K / 387 GB	5268	688
DeepSeek Coder V2 Base	160K / 387 GB	1566	81
DeepSeek V2 Chat	160K / 378.4 GB	10362	462
DeepSeek V2 Chat 0628	160K / 369.8 GB	5168	179
...eepSeek Coder V2 Instruct 0724	160K / 378.4 GB	358	117

Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/DeepSeek-V2.5-1210.