What are the hardware requirements for Deepseek Llm 67B Chat 2.4bpw H6 EXL2?

Deepseek Llm 67B Chat 2.4bpw H6 EXL2 requires approximately 22.2 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 2.4bpw H6 EXL2 and how large is it?

Deepseek Llm 67B Chat 2.4bpw H6 EXL2 is developed by LoneStriker, 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 2.4bpw H6 EXL2?

Deepseek Llm 67B Chat 2.4bpw H6 EXL2 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 2.4bpw H6 EXL2 by LoneStriker — VRAM 22.2GB, 4K context

Name: Deepseek Llm 67B Chat 2.4bpw H6 EXL2
Author: LoneStriker

Deepseek Llm 67B Chat 2.4bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 67b LLM, VRAM: 22.2GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.09.

Conversational Endpoints compatible Exl2 Llama Pytorch Quantized Region:us Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoneStriker/deepseek-llm-67b-chat-2.4bpw-h6-exl2

Deepseek Llm 67B Chat 2.4bpw H6 EXL2 Parameters and Internals

Model Type

text generation

Additional Notes

The model is open-source, comes with an MIT License for code, and is subject to a separate model license.

Supported Languages

English (fluent), Chinese (fluent)

Training Details

Data Volume:

2 trillion tokens

Methodology:

scratch with fine-tuning

Input Output

Input Format:

structured as chat messages

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Avoid using system prompts as they are not compatible with the model version.

LLM Name	Deepseek Llm 67B Chat 2.4bpw H6 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/deepseek-llm-67b-chat-2.4bpw-h6-exl2
Model Size	67b
Required VRAM	22.2 GB
Updated	2026-07-30
Maintainer	LoneStriker
Model Type	llama
Model Files	8.6 GB: 1-of-3 8.6 GB: 2-of-3 5.0 GB: 3-of-3
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.1
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 2.4bpw H6 EXL2 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 2.4bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
...67B Spicy 3.1 1 5.0bpw H6 EXL2	4K / 43.7 GB	5	1
...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
...ddy Deepseek 67B V18.1 4K Gptq	4K / 37.6 GB	8	2
...penbuddy Deepseek 67B V15.3 4K	4K / 135 GB	6	1
...penbuddy Deepseek 67B V15 Base	4K / 135 GB	94	0
Openbuddy Deepseek 67B V15.2	4K / 135 GB	106	10

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/deepseek-llm-67b-chat-2.4bpw-h6-exl2.