What are the hardware requirements for Llama 3 Stinky V2 8B?

Llama 3 Stinky V2 8B requires approximately 16 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 Stinky V2 8B and how large is it?

Llama 3 Stinky V2 8B is developed by nbeerbower, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3 Stinky V2 8B perform on standard benchmarks?

Llama 3 Stinky V2 8B has the following published scores: MMLU 68.33. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 Stinky V2 8B by nbeerbower — VRAM 16GB, 8K context

Name: Llama 3 Stinky V2 8B
Author: nbeerbower

Llama 3 Stinky V2 8B is an open-source language model by nbeerbower. Features: 8b LLM, VRAM: 16GB, Context: 8K, License: other, Instruction-Based, Merged, LLM Explorer Score: 0.13, Arc: 67, HellaSwag: 83.2, MMLU: 68.3, GSM8K: 69.8.

Merged Model Arxiv:2403.19522 Base model:cloudyu/meta-llama-... Base model:elyn-dev/llama-3-so... Base model:flammenai/mahou-1.0... Base model:flammenai/mahou-1.1... Base model:grimjim/llama-3-mer... Base model:grimjim/llama-3-mer... Base model:grimjim/llama-3-nvi... Base model:jeiku/orthocopter 8... Base model:mlabonne/chimeralla... Base model:nbeerbower/llama-3-... Base model:neversleep/llama-3-... Base model:uygarkurt/llama-3-m... Base model:vagosolutions/llama... Conversational Deploy:azure Endpoints compatible Instruct Llama Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nbeerbower/llama-3-stinky-v2-8B

Llama 3 Stinky V2 8B Parameters and Internals

Model Type

text generation

Additional Notes

This model was merged using the Model Stock merge method with the flammenai/Mahou-1.1-llama3-8B as a base. It includes various models listed under 'Models Merged'.

LLM Name	Llama 3 Stinky V2 8B
Repository 🤗	https://huggingface.co/nbeerbower/llama-3-stinky-v2-8B
Base Model(s)	ChimeraLlama 3 8B V2 Llama 3 Merge Pp Instruct 8B Llama 3 Merge Virt Req 8B Llama 3 Merged Linear Orthocopter 8B grimjim/llama-3-nvidia-ChatQA-1.5-8B Llama 3 Soliloquy 8B V2 ...ama 3 SauerkrautLM 8B Instruct Llama 3 Stella 8B Meta Llama 3 8B Instruct DPO NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS flammenai/Mahou-1.0-llama3-8B flammenai/Mahou-1.1-llama3-8B mlabonne/ChimeraLlama-3-8B-v2 grimjim/llama-3-merge-pp-instruct-8B grimjim/llama-3-merge-virt-req-8B uygarkurt/llama-3-merged-linear jeiku/Orthocopter_8B grimjim/llama-3-nvidia-ChatQA-1.5-8B openlynn/Llama-3-Soliloquy-8B-v2 VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct nbeerbower/llama-3-stella-8B cloudyu/Meta-Llama-3-8B-Instruct-DPO NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS flammenai/Mahou-1.0-llama3-8B flammenai/Mahou-1.1-llama3-8B
Merged Model	Yes
Model Size	8b
Required VRAM	16 GB
Updated	2026-07-14
Maintainer	nbeerbower
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-2 6.1 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.1
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3 Stinky V2 8B 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 Stinky V2 8B

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
Zero Llama 3.1 8B Beta6	1048K / 16.1 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than nbeerbower/llama-3-stinky-v2-8B.