What are the hardware requirements for Yarn Solar 10B 32K?

Yarn Solar 10B 32K requires approximately 21.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Yarn Solar 10B 32K and how large is it?

Yarn Solar 10B 32K 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 32K?

Yarn Solar 10B 32K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yarn Solar 10B 32K by NousResearch — VRAM 21.4GB, 32K context

Name: Yarn Solar 10B 32K
Author: NousResearch

Yarn Solar 10B 32K is an open-source language model by NousResearch. Features: 10b LLM, VRAM: 21.4GB, Context: 32K, 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-32k

Yarn Solar 10B 32K Parameters and Internals

Model Type

language model

Supported Languages

en (high)

Training Details

Data Sources:

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

Data Volume:

two billion long context tokens

Methodology:

YaRN extension method

Context Length:

32000

Hardware Used:

JUWELS supercomputer

Model Architecture:

extension of SOLAR-10.7B-v1.0

Input Output

Performance Tips:

Pass trust_remote_code=True when loading the model.

LLM Name	Yarn Solar 10B 32K
Repository 🤗	https://huggingface.co/NousResearch/Yarn-Solar-10b-32k
Model Size	10b
Required VRAM	21.4 GB
Updated	2026-07-15
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	32768
Model Max Length	32768
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Yarn Solar 10B 32K 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 32K

Model	Likes	Downloads	VRAM
Yarn Solar 10B 32K GGUF	1	234	4 GB

Best Alternatives to Yarn Solar 10B 32K

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
Yarn Solar 10B 64K	64K / 21.4 GB	150	16
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

Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Yarn-Solar-10b-32k.