What are the hardware requirements for Deepseek Llm 67B Chat GPTQ?

Deepseek Llm 67B Chat GPTQ requires approximately 36.3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Llm 67B Chat GPTQ and how large is it?

Deepseek Llm 67B Chat GPTQ 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 Chat GPTQ?

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

Deepseek Llm 67B Chat GPTQ by TheBloke — VRAM 36.3GB, 4K context

Name: Deepseek Llm 67B Chat GPTQ
Author: TheBloke

Deepseek Llm 67B Chat GPTQ is an open-source language model by TheBloke. Features: 67b LLM, VRAM: 36.3GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Conversational Gptq Llama Quantized Region:us Safetensors

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

Deepseek Llm 67B Chat GPTQ Parameters and Internals

Model Type

deepseek

Supported Languages

languages_supported (English, Chinese), proficiency (Not specified)

Training Details

Data Sources:

Not specified

Data Volume:

2 trillion tokens

Methodology:

Fine-tuned on extra instruction data

Input Output

Input Format:

User: {prompt} Assistant:

LLM Name	Deepseek Llm 67B Chat GPTQ
Repository 🤗	https://huggingface.co/TheBloke/deepseek-llm-67b-chat-GPTQ
Model Name	Deepseek Llm 67B Chat
Model Creator	DeepSeek
Base Model(s)	Deepseek Llm 67B Chat deepseek-ai/deepseek-llm-67b-chat
Model Size	67b
Required VRAM	36.3 GB
Updated	2026-07-14
Maintainer	TheBloke
Model Type	deepseek
Model Files	36.3 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
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 Llm 67B Chat GPTQ 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 Llm 67B Chat GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...ddy Deepseek 67B V18.1 4K Gptq	4K / 37.6 GB	8	2
...ddy Deepseek 67B V15 Base GPTQ	4K / 36.3 GB	5	0
Deepseek Llm 67B Base GPTQ	4K / 36.3 GB	10	1
...67B Spicy 3.1 1 5.0bpw H6 EXL2	4K / 43.7 GB	5	1
...ek Llm 67B Chat 2.4bpw H6 EXL2	4K / 22.2 GB	4	2
...ek Llm 67B Chat 3.0bpw H6 EXL2	4K / 27.1 GB	4	1
...k Llm 67B Chat 2.65bpw H6 EXL2	4K / 24.2 GB	3	1
Deepseek Llm 67B Chat	4K / 135 GB	1034	207
...penbuddy Deepseek 67B V18.1 4K	4K / 135 GB	8526	1
Deepseek Llm 67B Base	4K / 135 GB	9029	130

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