What are the hardware requirements for LLaMa 3 Stheno V3.2 15B?

LLaMa 3 Stheno V3.2 15B requires approximately 30 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LLaMa 3 Stheno V3.2 15B and how large is it?

LLaMa 3 Stheno V3.2 15B is developed by PJMixers, a model with 15b 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 LLaMa 3 Stheno V3.2 15B?

LLaMa 3 Stheno V3.2 15B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LLaMa 3 Stheno V3.2 15B by PJMixers — VRAM 30GB, 8K context

Name: LLaMa 3 Stheno V3.2 15B
Author: PJMixers

LLaMa 3 Stheno V3.2 15B is an open-source language model by PJMixers. Features: 15b LLM, VRAM: 30GB, Context: 8K, Instruction-Based, Merged, LLM Explorer Score: 0.13.

Merged Model Arxiv:2212.04089 Autotrain compatible Base model:elinas/llama-3-15b-... Base model:elinas/llama-3-15b-... Base model:pjmixers/llama-3-st... Conversational Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/PJMixers/LLaMa-3-Stheno-v3.2-15B

LLaMa 3 Stheno V3.2 15B Parameters and Internals

LLM Name	LLaMa 3 Stheno V3.2 15B
Repository 🤗	https://huggingface.co/PJMixers/LLaMa-3-Stheno-v3.2-15B
Base Model(s)	Llama 3 15B Instruct Zeroed Llama 3 15B Instruct Ft V2 PJMixers/LLaMa-3-Stheno-v3.2-Zeroed-15B elinas/Llama-3-15B-Instruct-zeroed elinas/Llama-3-15B-Instruct-ft-v2 PJMixers/LLaMa-3-Stheno-v3.2-Zeroed-15B
Merged Model	Yes
Model Size	15b
Required VRAM	30 GB
Updated	2024-12-02
Maintainer	PJMixers
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-7 5.0 GB: 2-of-7 4.9 GB: 3-of-7 4.9 GB: 4-of-7 5.0 GB: 5-of-7 4.9 GB: 6-of-7 0.3 GB: 7-of-7
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the LLaMa 3 Stheno V3.2 15B 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 LLaMa 3 Stheno V3.2 15B

Best Alternatives	Context / RAM	Downloads	Likes
Hamanasu 15B Instruct	16K / 29.4 GB	473	9
L3 Aethora 15B V2	8K / 30.1 GB	22	42
Meta Llama 3 15B Instruct	8K / 23.9 GB	3	1
OpenCrystal 15B L3 V3	8K / 30 GB	13	10
OpenCrystal L3 15B V2.1	8K / 30 GB	3	5
OpenCrystal 15B L3 V2	8K / 30 GB	3	6
Llama 3 15B Instruct Ft V2	8K / 30.1 GB	13	4
Llama 3 15B Instruct Zeroed Ft	8K / 30.1 GB	19	2
L3 Aethora 15B V2	8K / 30.1 GB	29	44
L3 NA Aethora 15B	8K / 30.1 GB	7	3

Note: green Score (e.g. "73.2") means that the model is better than PJMixers/LLaMa-3-Stheno-v3.2-15B.