What are the hardware requirements for Llama 3.2 Kapusta 3B V8?

Llama 3.2 Kapusta 3B V8 requires approximately 7.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3.2 Kapusta 3B V8 and how large is it?

Llama 3.2 Kapusta 3B V8 is developed by Khetterman, a model with 3b 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 3.2 Kapusta 3B V8?

Llama 3.2 Kapusta 3B V8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3.2 Kapusta 3B V8 by Khetterman — VRAM 7.2GB, 128K context

Name: Llama 3.2 Kapusta 3B V8
Author: Khetterman

Llama 3.2 Kapusta 3B V8 is an open-source language model by Khetterman. Features: 3b LLM, VRAM: 7.2GB, Context: 128K, Instruction-Based, Merged, LLM Explorer Score: 0.15.

Merged Model 3b Autotrain compatible Base model:bunnycore/llama-3.2... Base model:bunnycore/llama-3.2... Base model:bunnycore/llama-3.2... Base model:bunnycore/llama-3.2... Base model:bunnycore/llama-3.2... Base model:carrotai/llama-3.2-... Base model:devarui379/versatil... Base model:hastagaras/l3.2-jam... Base model:huihui-ai/llama-3.2... Base model:lyte/llama-3.2-3b-o... Base model:passing2961/thanos-... Base model:saisexperiments/evi... Base model:valiantlabs/llama3.... Base model:valiantlabs/llama3.... Bfloat16 Chat Conversational Creative En Endpoints compatible Instruct Llama Llama-3 Llama-3.2 Not-for-all-audiences Region:us Ru Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Khetterman/Llama-3.2-Kapusta-3B-v8

Llama 3.2 Kapusta 3B V8 Parameters and Internals

LLM Name	Llama 3.2 Kapusta 3B V8
Repository 🤗	https://huggingface.co/Khetterman/Llama-3.2-Kapusta-3B-v8
Base Model(s)	bunnycore/Llama-3.2-3B-Creative bunnycore/Llama-3.2-3B-Mix bunnycore/Llama-3.2-3B-Pure-RP bunnycore/Llama-3.2-3B-Stock bunnycore/Llama-3.2-3B-TitanFusion-v2 CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated Hastagaras/L3.2-JametMini-3B-MK.III huihui-ai/Llama-3.2-3B-Instruct-abliterated Lyte/Llama-3.2-3B-Overthinker Thanos 3B SaisExperiments/Evil-Alpaca-3B-L3.2 ValiantLabs/Llama3.2-3B-Enigma ValiantLabs/Llama3.2-3B-ShiningValiant2 bunnycore/Llama-3.2-3B-Creative bunnycore/Llama-3.2-3B-Mix bunnycore/Llama-3.2-3B-Pure-RP bunnycore/Llama-3.2-3B-Stock bunnycore/Llama-3.2-3B-TitanFusion-v2 CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated Hastagaras/L3.2-JametMini-3B-MK.III huihui-ai/Llama-3.2-3B-Instruct-abliterated Lyte/Llama-3.2-3B-Overthinker passing2961/Thanos-3B SaisExperiments/Evil-Alpaca-3B-L3.2 ValiantLabs/Llama3.2-3B-Enigma ValiantLabs/Llama3.2-3B-ShiningValiant2
Merged Model	Yes
Model Size	3b
Required VRAM	7.2 GB
Updated	2025-09-23
Maintainer	Khetterman
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.2 GB: 2-of-2
Supported Languages	en ru
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3.2 Kapusta 3B V8 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 3.2 Kapusta 3B V8

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
Llama 3.2 3B Instruct	128K / 6.5 GB	186207	96
Llama3.2 3B Manumit V1	128K / 6.4 GB	135	0
Llama 3.2 3B Instruct	128K / 6.5 GB	991	9
Alloma 3B Instruct	128K / 6.5 GB	55456	6
... V7 SFT 10voicebot Loopcleaned	128K / 6.5 GB	229	0
Llama 3.2 3B RP Toxic Fuse	128K / 6.4 GB	14	2
DeepSeek R1 Distill Llama 3B	128K / 6.5 GB	247	16
Schematron 3B	128K / 6.5 GB	969	336
ReasoningCore 3B T1 1	128K / 6.5 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than Khetterman/Llama-3.2-Kapusta-3B-v8.