What are the hardware requirements for L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B?

L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B requires approximately 54.9 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B and how large is it?

L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B is developed by DavidAU, a model with 13.7b 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 L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B?

L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B by DavidAU — VRAM 54.9GB, 128K context

Name: L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B
Author: DavidAU

L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B is an open-source language model by DavidAU. Features: 13.7b LLM, VRAM: 54.9GB, Context: 128K, MoE, LLM Explorer Score: 0.17.

128k context Autotrain compatible Base model:deepseek-ai/deepsee... Base model:merge:deepseek-ai/d... Base model:merge:nousresearch/... Base model:nousresearch/deephe... Cognitivecomputations Conversational Cot Deephermes Deepseek Endpoints compatible Fine tune Hermes Llama 3.1 Llama-3 Llama-3.1 Llama3 Merge Mixtral Moe R1 Reasoning Region:us Safetensors Sharded Tensorflow Thinking

Model Card on HF 🤗: https://huggingface.co/DavidAU/L3.1-MOE-2X8B-Deepseek-DeepHermes-e32-13.7B

L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B Parameters and Internals

LLM Name	L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B
Repository 🤗	https://huggingface.co/DavidAU/L3.1-MOE-2X8B-Deepseek-DeepHermes-e32-13.7B
Base Model(s)	...eepHermes 3 Llama 3 8B Preview DeepSeek R1 Distill Llama 8B NousResearch/DeepHermes-3-Llama-3-8B-Preview deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Model Size	13.7b
Required VRAM	54.9 GB
Updated	2025-09-18
Maintainer	DavidAU
Model Type	mixtral
Model Files	4.8 GB: 1-of-12 5.0 GB: 2-of-12 5.0 GB: 3-of-12 4.9 GB: 4-of-12 5.0 GB: 5-of-12 5.0 GB: 6-of-12 5.0 GB: 7-of-12 5.0 GB: 8-of-12 5.0 GB: 9-of-12 5.0 GB: 10-of-12 3.1 GB: 11-of-12 2.1 GB: 12-of-12
Model Architecture	MixtralForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.2
Tokenizer Class	LlamaTokenizer
Padding Token	<｜begin▁of▁sentence｜>
Vocabulary Size	128256
Torch Data Type	float32

Rank the L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B 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 L3.1 MoE 2X8B Deepseek DeepHermes E32 13.7B

Best Alternatives	Context / RAM	Downloads	Likes
L3.1 MoE 2x8B V0.2	128K / 27.3 GB	9	9
HAI SER	128K / 27.3 GB	7	16
L3.1 Celestial Stone 2x8B	128K / 27.3 GB	312	3
...ma 3 2x8B Instruct MoE 64K Ctx	64K / 27.3 GB	12	4
Penny Llama3 2x8b	8K / 27.3 GB	6	1
Kilo 2x8B	8K / 27.5 GB	12	1
Defne Llama3 2x8B	8K / 27.4 GB	15	6
Llama 3 Elyza Youko MoE 2x8B	8K / 27.3 GB	10	0
Llama 3 ELYZA Hermes 2x8B	8K / 27.4 GB	3	1
Inixion 2x8B V2	8K / 27.4 GB	6	2

Note: green Score (e.g. "73.2") means that the model is better than DavidAU/L3.1-MOE-2X8B-Deepseek-DeepHermes-e32-13.7B.