What are the hardware requirements for Deepseek Llm 67B Base GGUF?

Deepseek Llm 67B Base GGUF requires approximately 28.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Llm 67B Base GGUF and how large is it?

Deepseek Llm 67B Base GGUF is developed by TheBloke, a model with 67b 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 Llm 67B Base GGUF?

Deepseek Llm 67B Base GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Llm 67B Base GGUF by TheBloke — VRAM 28.5GB

Name: Deepseek Llm 67B Base GGUF
Author: TheBloke

Deepseek Llm 67B Base GGUF is an open-source language model by TheBloke. Features: 67b LLM, VRAM: 28.5GB, License: other, Quantized, LLM Explorer Score: 0.11.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Gguf Quantized Region:us Yi

Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF

Deepseek Llm 67B Base GGUF Benchmarks

LLME Score: 0.10689

^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 Llm 67B Base GGUF (TheBloke/deepseek-llm-67b-base-GGUF)

🌟 Advertise your project 🚀

Deepseek Llm 67B Base GGUF Parameters and Internals

Model Type

Supported Languages

languages_supported (English and Chinese), proficiency_level (High)

Training Details

Data Volume:

2 trillion tokens

Model Architecture:

Grouped-Query Attention

Input Output

Input Format:

{prompt}

Accepted Modalities:

text

LLM Name	Deepseek Llm 67B Base GGUF
Repository 🤗	https://huggingface.co/TheBloke/deepseek-llm-67b-base-GGUF
Model Name	Deepseek LLM 67B Base
Model Creator	DeepSeek
Base Model(s)	Deepseek Llm 67B Base deepseek-ai/deepseek-llm-67b-base
Model Size	67b
Required VRAM	28.5 GB
Updated	2026-06-16
Maintainer	TheBloke
Model Type	yi
Model Files	28.5 GB 35.6 GB 32.6 GB 29.3 GB 38.2 GB 40.4 GB 38.2 GB 46.5 GB 47.7 GB 46.5 GB
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModel
License	other

Best Alternatives to Deepseek Llm 67B Base GGUF

Best Alternatives	Context / RAM	Downloads	Likes
Deepseek Llm 67B Chat GGUF	0K / 28.5 GB	3064	43
...ddy Deepseek 67B V15 Base GGUF	0K / 28.5 GB	426	3

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-llm-67b-base-GGUF.

Rank the Deepseek Llm 67B Base GGUF Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 54415 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Deepseek Llm 67B Base GGUF by TheBloke

» All LLMs » TheBloke » Deepseek Llm 67B Base GGUF URL Share it on

Deepseek Llm 67B Base GGUF Benchmarks

Deepseek Llm 67B Base GGUF Parameters and Internals

Best Alternatives to Deepseek Llm 67B Base GGUF

Rank the Deepseek Llm 67B Base GGUF Capabilities

What open-source LLMs or SLMs are you in search of? 54415 in total.