What are the hardware requirements for H2ogpt Research Oasst1 Llama 65B?

H2ogpt Research Oasst1 Llama 65B requires approximately 131.7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed H2ogpt Research Oasst1 Llama 65B and how large is it?

H2ogpt Research Oasst1 Llama 65B is developed by h2oai, a model with 65b 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 H2ogpt Research Oasst1 Llama 65B?

H2ogpt Research Oasst1 Llama 65B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

H2ogpt Research Oasst1 Llama 65B by h2oai — VRAM 131.7GB, 2K context

Name: H2ogpt Research Oasst1 Llama 65B
Author: h2oai

H2ogpt Research Oasst1 Llama 65B is an open-source language model by h2oai. Features: 65b LLM, VRAM: 131.7GB, Context: 2K, License: other, LLM Explorer Score: 0.07.

Dataset:h2oai/openassistant oa... En Gpt Llama Open-source Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b

H2ogpt Research Oasst1 Llama 65B Parameters and Internals

Model Type

instruction-following, large language model

Training Details

Data Sources:

h2oai/openassistant_oasst1_h2ogpt_graded

Model Architecture:

LlamaForCausalLM, with 80 LlamaDecoderLayers and embedding size of 8192

LLM Name	H2ogpt Research Oasst1 Llama 65B
Repository 🤗	https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b
Model Size	65b
Required VRAM	131.7 GB
Updated	2026-06-07
Maintainer	h2oai
Model Type	llama
Model Files	4.7 GB: 1-of-27 4.9 GB: 2-of-27 4.9 GB: 3-of-27 4.9 GB: 4-of-27 4.9 GB: 5-of-27 4.9 GB: 6-of-27 4.9 GB: 7-of-27 4.9 GB: 8-of-27 4.9 GB: 9-of-27 4.9 GB: 10-of-27 4.9 GB: 11-of-27 4.9 GB: 12-of-27 4.9 GB: 13-of-27 4.9 GB: 14-of-27 4.9 GB: 15-of-27 4.9 GB: 16-of-27 4.9 GB: 17-of-27 4.9 GB: 18-of-27 4.9 GB: 19-of-27 4.9 GB: 20-of-27 4.9 GB: 21-of-27 4.9 GB: 22-of-27 4.9 GB: 23-of-27 4.9 GB: 24-of-27 4.9 GB: 25-of-27 4.9 GB: 26-of-27 4.5 GB: 27-of-27
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.30.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the H2ogpt Research Oasst1 Llama 65B 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

Quantized Models of the H2ogpt Research Oasst1 Llama 65B

Model	Likes	Downloads	VRAM
...Research Oasst1 Llama 65B GPTQ	5	11	33 GB

Best Alternatives to H2ogpt Research Oasst1 Llama 65B

Best Alternatives	Context / RAM	Downloads	Likes
Kiyo 65M	2K / 0.1 GB	1456	2
Lite Oute 1 65M	2K / 0.3 GB	23	12
Lite Oute 1 65M Instruct	2K / 0.3 GB	15	12
StableBeluga1 Delta	2K / 130.4 GB	146	57
Airoboros 65B Gpt4 M2.0	2K / 130.4 GB	850	0
Airoboros 65B Gpt4 2.0	2K / 130.4 GB	435	0
UltraLM 65B	2K / 130.4 GB	348	9
Openbuddy Llama 65B V8 Bf16	2K / 130.6 GB	177	9
Airoboros 65B Gpt4 1.4	2K / 130.4 GB	163	17
Llama 1 65B Hf	2K / 130.4 GB	14	1

Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2ogpt-research-oasst1-llama-65b.