What are the hardware requirements for Nous Hermes 2 MoE 2x34B?

Nous Hermes 2 MoE 2x34B requires approximately 121.9 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 Nous Hermes 2 MoE 2x34B and how large is it?

Nous Hermes 2 MoE 2x34B is developed by ibndias, a model with 60.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Nous Hermes 2 MoE 2x34B perform on standard benchmarks?

Nous Hermes 2 MoE 2x34B has the following published scores: MMLU 76.49. Compare against reference models on this page or on the LLM Explorer leaderboards.

Nous Hermes 2 MoE 2x34B by ibndias — VRAM 121.9GB, 4K context

Name: Nous Hermes 2 MoE 2x34B
Author: ibndias

Nous Hermes 2 MoE 2x34B is an open-source language model by ibndias. Features: 60.8b LLM, VRAM: 121.9GB, Context: 4K, License: apache-2.0, MoE, LLM Explorer Score: 0.11, Arc: 66.6, HellaSwag: 85.7, MMLU: 76.5, GSM8K: 69.5.

Endpoints compatible Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibndias/Nous-Hermes-2-MoE-2x34B

Nous Hermes 2 MoE 2x34B Parameters and Internals

Model Type

text generation

Additional Notes

This is an experimental model to make an MoE (Mixture of Expert) of Nous Hermes 2 Yi 34B.

Training Details

Methodology:

Mixture of Expert

LLM Name	Nous Hermes 2 MoE 2x34B
Repository 🤗	https://huggingface.co/ibndias/Nous-Hermes-2-MoE-2x34B
Model Size	60.8b
Required VRAM	121.9 GB
Updated	2026-07-05
Maintainer	ibndias
Model Type	mixtral
Model Files	9.8 GB: 1-of-13 10.0 GB: 2-of-13 10.0 GB: 3-of-13 10.0 GB: 4-of-13 10.0 GB: 5-of-13 10.0 GB: 6-of-13 10.0 GB: 7-of-13 10.0 GB: 8-of-13 10.0 GB: 9-of-13 10.0 GB: 10-of-13 10.0 GB: 11-of-13 10.0 GB: 12-of-13 2.1 GB: 13-of-13
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|startoftext\|>
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the Nous Hermes 2 MoE 2x34B 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 Nous Hermes 2 MoE 2x34B

Best Alternatives	Context / RAM	Downloads	Likes
Mixtral 34Bx2 MoE 60B	195K / 121.9 GB	7876	114
Yi 34Bx2 MoE 60B DPO	195K / 121.8 GB	8035	3
Bagel Hermes 2x34B	195K / 121.9 GB	70	16
Yi 34Bx2 MoE 200K	195K / 121.9 GB	7897	2
Yi 34Bx2 MoE 60B	195K / 121.9 GB	7954	64
...34Bx2 MoE V0.1 Full Linear DPO	195K / 121.8 GB	68	2
FusionNet 34Bx2 MoE V0.1	195K / 121.2 GB	52	8
... Cloudyu Mixtral 34Bx2 MoE 60B	195K / 121.8 GB	57	0
...DPO TomGrc FusionNet 34Bx2 MoE	32K / 121.8 GB	81	4
FusionNet 34Bx2 MoE	32K / 121.2 GB	65	9

Note: green Score (e.g. "73.2") means that the model is better than ibndias/Nous-Hermes-2-MoE-2x34B.