What are the hardware requirements for TildeOpen 30B 64K?

TildeOpen 30B 64K requires approximately 60.9 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TildeOpen 30B 64K and how large is it?

TildeOpen 30B 64K is developed by TildeAI, 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 TildeOpen 30B 64K?

TildeOpen 30B 64K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TildeOpen 30B 64K by TildeAI — VRAM 60.9GB, 64K context

Name: TildeOpen 30B 64K
Author: TildeAI

TildeOpen 30B 64K is an open-source language model by TildeAI. Features: 30b LLM, VRAM: 60.9GB, Context: 64K, License: cc-by-4.0, LLM Explorer Score: 0.24.

Arxiv:1803.05457 Arxiv:2009.03300 Arxiv:2309.00071 Arxiv:2409.04774 Arxiv:2410.08928 Arxiv:2412.19437 Arxiv:2504.02768 Arxiv:2603.08182 Bg Bs Cs Custom code Da Dataset:allenai/madlad-400 Dataset:bigcode/the-stack Dataset:common-pile/arxiv pape... Dataset:hplt/hplt2.0 cleaned Dataset:hplt/hplt monolingual ... Dataset:huggingfacefw/finepdfs Dataset:huggingfacefw/fineweb-... Dataset:uonlp/culturax De En Endpoints compatible Es Et Fi Fr Ga Hr Hu Is It Llama Lt Lv Mk Mt Nl No Pl Pt Region:us Ro Ru Safetensors Sharded Sk Sl Sq Sr Sv Tensorflow Tr Uk

Model Card on HF 🤗: https://huggingface.co/TildeAI/TildeOpen-30b-64k

TildeOpen 30B 64K Parameters and Internals

LLM Name	TildeOpen 30B 64K
Repository 🤗	https://huggingface.co/TildeAI/TildeOpen-30b-64k
Model Size	30b
Required VRAM	60.9 GB
Updated	2026-08-18
Maintainer	TildeAI
Model Type	llama
Model Files	5.0 GB: 1-of-13 4.8 GB: 2-of-13 4.8 GB: 3-of-13 4.8 GB: 4-of-13 4.8 GB: 5-of-13 4.8 GB: 6-of-13 4.8 GB: 7-of-13 4.8 GB: 8-of-13 4.8 GB: 9-of-13 4.8 GB: 10-of-13 4.8 GB: 11-of-13 4.8 GB: 12-of-13 3.1 GB: 13-of-13
Supported Languages	en de fr pl ru it pt cs nl es fi tr hu bg uk bs hr da et lt ro sk sl sv no lv sr sq mk is mt ga
Model Architecture	LlamaForCausalLM
License	cc-by-4.0
Context Length	65536
Model Max Length	65536
Transformers Version	4.46.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the TildeOpen 30B 64K 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 TildeOpen 30B 64K

Best Alternatives	Context / RAM	Downloads	Likes
TildeOpen 30B	64K / 60.9 GB	4576	165
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
Llama33b 16K	16K / 65.2 GB	1	1
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 TildeAI/TildeOpen-30b-64k.