What are the hardware requirements for Sd2?

Sd2 requires approximately 215.4 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 Sd2 and how large is it?

Sd2 is developed by Delta-Vector, a model with 70b 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 Sd2?

Sd2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sd2 by Delta-Vector — VRAM 215.4GB, 128K context

Name: Sd2
Author: Delta-Vector

Sd2 is an open-source language model by Delta-Vector. Features: 70b LLM, VRAM: 215.4GB, Context: 128K, License: llama3.3, LLM Explorer Score: 0.19.

70b Autotrain compatible Axolotl Base model:finetune:sao10k/lla... Base model:sao10k/llama-3.3-70... Conversational Creative-writing Dataset:anthracite-org/kalo mi... Dataset:anthracite-org/kalo op... Dataset:neweden/bluesky-10k-co... Dataset:neweden/books-v2-share... Dataset:neweden/creative writi... Dataset:neweden/deepseek-v3-rp... Dataset:neweden/deepseekrp-fil... Dataset:neweden/final-alpindal... Dataset:neweden/light-novels-r... Dataset:neweden/limarp-complex... Dataset:neweden/opencai-shareg... Dataset:neweden/pippa-mega-fil... Dataset:neweden/rp-logs-v2-exp... Dataset:neweden/storium-prefix... Dataset:neweden/vanilla-backro... Dataset:pocketdoc/dans-failure... Dataset:pocketdoc/dans-persona... En Endpoints compatible Finetuned Llama Region:us Roleplay Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Edens-Gate/sd2

Sd2 Parameters and Internals

LLM Name	Sd2
Repository 🤗	https://huggingface.co/Edens-Gate/sd2
Base Model(s)	Sao10K/Llama-3.3-70B-Vulpecula-r1 Sao10K/Llama-3.3-70B-Vulpecula-r1
Model Size	70b
Required VRAM	215.4 GB
Updated	2025-06-23
Maintainer	Delta-Vector
Model Type	llama
Model Files	4.2 GB: 1-of-62 4.2 GB: 2-of-62 4.4 GB: 3-of-62 4.4 GB: 4-of-62 5.0 GB: 5-of-62 4.4 GB: 6-of-62 4.4 GB: 7-of-62 5.0 GB: 8-of-62 4.4 GB: 9-of-62 4.4 GB: 10-of-62 5.0 GB: 11-of-62 4.4 GB: 12-of-62 4.4 GB: 13-of-62 5.0 GB: 14-of-62 4.4 GB: 15-of-62 4.4 GB: 16-of-62 5.0 GB: 17-of-62 4.4 GB: 18-of-62 4.4 GB: 19-of-62 5.0 GB: 20-of-62 4.4 GB: 21-of-62 4.4 GB: 22-of-62 5.0 GB: 23-of-62 4.4 GB: 24-of-62 4.4 GB: 25-of-62 5.0 GB: 26-of-62 4.4 GB: 27-of-62 4.4 GB: 28-of-62 5.0 GB: 29-of-62 4.4 GB: 30-of-62 4.7 GB: 31-of-62 4.7 GB: 32-of-62 4.4 GB: 33-of-62 4.4 GB: 34-of-62 5.0 GB: 35-of-62 4.4 GB: 36-of-62 4.4 GB: 37-of-62 5.0 GB: 38-of-62 4.4 GB: 39-of-62 4.4 GB: 40-of-62 5.0 GB: 41-of-62 4.4 GB: 42-of-62 4.4 GB: 43-of-62 5.0 GB: 44-of-62 4.4 GB: 45-of-62 4.4 GB: 46-of-62 5.0 GB: 47-of-62
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama3.3
Context Length	131072
Model Max Length	131072
Transformers Version	4.49.0
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Sd2 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 Sd2

Best Alternatives	Context / RAM	Downloads	Likes
... Chat 1048K Chinese Llama3 70B	1024K / 141.9 GB	9069	5
... Chat 1048K Chinese Llama3 70B	1024K / 141.9 GB	7684	4
... 3 70B Instruct Gradient 1048K	1024K / 141.9 GB	22	122
Llama3 Function Calling 1048K	1024K / 141.9 GB	5	1
...a 3 70B Instruct Gradient 524K	512K / 141.9 GB	24	23
...a 3 70B Instruct Gradient 262K	256K / 141.9 GB	20	56
...ama 3 70B Arimas Story RP V2.0	256K / 141.1 GB	10	3
...ama 3 70B Arimas Story RP V1.6	256K / 141.2 GB	5	0
...ama 3 70B Arimas Story RP V1.5	256K / 141.2 GB	21	3
Yi 70B 200K RPMerge Franken	195K / 142.4 GB	9	1