What are the hardware requirements for Yarn Solar 10B 64K?

Yarn Solar 10B 64K requires approximately 21.4 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Yarn Solar 10B 64K and how large is it?

Yarn Solar 10B 64K is developed by NousResearch, a model with 10b 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 Yarn Solar 10B 64K?

Yarn Solar 10B 64K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yarn Solar 10B 64K by NousResearch — VRAM 21.4GB, 64K context

Name: Yarn Solar 10B 64K
Author: NousResearch

Yarn Solar 10B 64K is an open-source language model by NousResearch. Features: 10b LLM, VRAM: 21.4GB, Context: 64K, License: apache-2.0, LLM Explorer Score: 0.15.

Arxiv:2309.00071 Custom code Dataset:emozilla/yarn-train-to... En Endpoints compatible Llama Pytorch Region:us Sharded Yarn

Model Card on HF 🤗: https://huggingface.co/NousResearch/Yarn-Solar-10b-64k

Yarn Solar 10B 64K Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Additional Notes

Authors thank LAION AI for compute support.

Supported Languages

en (proficient)

Training Details

Data Sources:

emoZilla/yarn-train-tokenized-32k-mistral

Data Volume:

two billion long context tokens

Methodology:

extension method using YaRN

Context Length:

64000

Hardware Used:

JUWELS supercomputer

Input Output

Accepted Modalities:

text

Output Format:

text

Performance Tips:

pass 'trust_remote_code=True' when loading the model

LLM Name	Yarn Solar 10B 64K
Repository 🤗	https://huggingface.co/NousResearch/Yarn-Solar-10b-64k
Model Size	10b
Required VRAM	21.4 GB
Updated	2026-07-08
Maintainer	NousResearch
Model Type	llama
Model Files	4.9 GB: 1-of-5 5.0 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 1.7 GB: 5-of-5
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	65536
Model Max Length	65536
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Yarn Solar 10B 64K 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 Yarn Solar 10B 64K

Model	Likes	Downloads	VRAM
Yarn Solar 10B 64K GGUF	1	438	4 GB

Best Alternatives to Yarn Solar 10B 64K

Best Alternatives	Context / RAM	Downloads	Likes
...enbuddy Falcon3 10B V24.2 131K	128K / 20.7 GB	6	0
Priya 10B	128K / 20.5 GB	11	2
HelpingAI2.5 10B	128K / 20.5 GB	66	2
L3.1 Mochav2 10B	128K / 42.8 GB	21	0
HELVETE X	128K / 20.5 GB	104	11
HelpingAI2.5 10B	128K / 20.5 GB	9	8
StoryTeller 10B 2e V2	58K / 21.4 GB	5	1
Falcon3 10B Instruct	32K / 20.5 GB	7371	117
Virtuoso Lite	32K / 20.5 GB	23	38
Falcon3 10B Tensopolis V2	32K / 20.5 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Yarn-Solar-10b-64k.