What are the hardware requirements for Llama33b 16K?

Llama33b 16K requires approximately 65.2 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama33b 16K and how large is it?

Llama33b 16K is developed by chargoddard, a model with 30b 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 Llama33b 16K?

Llama33b 16K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama33b 16K by chargoddard — VRAM 65.2GB, 16K context

Name: Llama33b 16K
Author: chargoddard

Llama33b 16K is an open-source language model by chargoddard. Features: 30b LLM, VRAM: 65.2GB, Context: 16K, LLM Explorer Score: 0.08.

Dataset:eleutherai/wikitext do... Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/chargoddard/llama33b-16k

Llama33b 16K Parameters and Internals

Model Type

base model

Additional Notes

This is a merged version of llama33b-16k-qlora. It is not an instruct model but rather a base LLaMA with an extended sequence length.

Training Details

Data Sources:

EleutherAI/wikitext_document_level

Methodology:

fine-tuning with linear ROPE scaling of 8

Context Length:

16000

LLM Name	Llama33b 16K
Repository 🤗	https://huggingface.co/chargoddard/llama33b-16k
Model Size	30b
Required VRAM	65.2 GB
Updated	2026-07-25
Maintainer	chargoddard
Model Type	llama
Model Files	9.8 GB: 1-of-7 10.0 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 10.0 GB: 6-of-7 5.7 GB: 7-of-7
Model Architecture	LlamaForCausalLM
Context Length	16384
Model Max Length	16384
Transformers Version	4.31.0.dev0
Vocabulary Size	32000
Torch Data Type	float16

Rank the Llama33b 16K 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 Llama33b 16K

Best Alternatives	Context / RAM	Downloads	Likes
TildeOpen 30B	64K / 60.9 GB	4576	165
TildeOpen 30B 64K	64K / 60.9 GB	702	3
Tildeopen 30B Mu Instruct	64K / 60.9 GB	41	6
Flash Llama 30M 20001	32K / 0.1 GB	134	0
Smaug Slerp 30B V0.1	32K / 60.4 GB	79	0
Tenebra 30B Alpha01	16K / 65 GB	50	16
Veyra2 Mango 30M Base	4K / 0.1 GB	0	5
Yayi2 30B Llama	4K / 121.2 GB	922	22
... Tokens By Perplexity Bottom K	4K / 5.4 GB	8	0
...via Sample With Temperature2.0	4K / 5.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than chargoddard/llama33b-16k.