What are the hardware requirements for Nous Hermes 2 Yi 34B Marlin?

Nous Hermes 2 Yi 34B Marlin requires approximately 19.1 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 Yi 34B Marlin and how large is it?

Nous Hermes 2 Yi 34B Marlin is developed by RedHatAI, a model with 34b 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 Yi 34B Marlin perform on standard benchmarks?

Nous Hermes 2 Yi 34B Marlin has the following published scores: MMLU 76.7. Compare against reference models on this page or on the LLM Explorer leaderboards.

Nous Hermes 2 Yi 34B Marlin by RedHatAI — VRAM 19.1GB, 4K context

Name: Nous Hermes 2 Yi 34B Marlin
Author: RedHatAI

Nous Hermes 2 Yi 34B Marlin is an open-source language model by RedHatAI. Features: 34b LLM, VRAM: 19.1GB, Context: 4K, Quantized, LLM Explorer Score: 0.12, Arc: 66.9, HellaSwag: 85.5, MMLU: 76.7, GSM8K: 70.1.

Arxiv:2210.17323 4-bit Base model:nousresearch/nous-h... Base model:quantized:nousresea... Conversational Endpoints compatible Gptq Int4 Llama Marlin Nm-vllm Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/RedHatAI/Nous-Hermes-2-Yi-34B-marlin

Nous Hermes 2 Yi 34B Marlin Parameters and Internals

LLM Name	Nous Hermes 2 Yi 34B Marlin
Repository 🤗	https://huggingface.co/RedHatAI/Nous-Hermes-2-Yi-34B-marlin
Base Model(s)	Nous Hermes 2 Yi 34B NousResearch/Nous-Hermes-2-Yi-34B
Model Size	34b
Required VRAM	19.1 GB
Updated	2026-08-08
Maintainer	RedHatAI
Model Type	llama
Model Files	19.1 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	float16

Rank the Nous Hermes 2 Yi 34B Marlin 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 Yi 34B Marlin

Best Alternatives	Context / RAM	Downloads	Likes
Yi 34B 200K RPMerge GPTQ	195K / 21.2 GB	2	4
Smaug 34B V0.1 GPTQ	195K / 21.2 GB	1	1
Tess 34B V1.5B GPTQ	195K / 18.6 GB	18	8
...4B 200K DARE Megamerge V8 GPTQ	195K / 18.6 GB	4	3
...y 34B 200K Chat Evaluator GPTQ	195K / 18.6 GB	8	3
Deepmoney 34B 200K Base GPTQ	195K / 18.6 GB	3	3
...ous Capybara Limarpv3 34B GPTQ	195K / 18.6 GB	11	4
Bagel 34B V0.2 GPTQ	195K / 18.6 GB	7	2
Bagel DPO 34B V0.2 GPTQ	195K / 18.6 GB	5	2
Nontoxic Bagel 34B V0.2 GPTQ	195K / 18.6 GB	3	1