What are the hardware requirements for Saily 100B?

Saily 100B requires approximately 235.5 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Saily 100B and how large is it?

Saily 100B is developed by deepnight-research, a model with 100b 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 Saily 100B?

Saily 100B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Saily 100B by deepnight-research — VRAM 235.5GB, 4K context

Name: Saily 100B
Author: deepnight-research

Saily 100B is an open-source language model by deepnight-research. Features: 100b LLM, VRAM: 235.5GB, Context: 4K, License: mit, LLM Explorer Score: 0.1.

Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/deepnight-research/saily_100b

Saily 100B Parameters and Internals

Model Type

text generation

Additional Notes

SaiLy is highly experimental and uncensored. Please use with responsibility. The model is awaiting evaluation and submission on the HuggingFace OpenLLM Leaderboard.

Input Output

Input Format:

Alpaca

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use optimized triton implementation of FlashAttention and load the model on GPU (cuda:0) with bfloat16 precision for best performance.

LLM Name	Saily 100b
Repository 🤗	https://huggingface.co/deepnight-research/saily_100b
Model Size	100b
Required VRAM	235.5 GB
Updated	2026-07-27
Maintainer	deepnight-research
Model Type	llama
Model Files	9.8 GB: 1-of-24 9.8 GB: 2-of-24 10.0 GB: 3-of-24 9.9 GB: 4-of-24 9.8 GB: 5-of-24 9.8 GB: 6-of-24 9.9 GB: 7-of-24 9.7 GB: 8-of-24 9.8 GB: 9-of-24 10.0 GB: 10-of-24 10.0 GB: 11-of-24 9.9 GB: 12-of-24 9.9 GB: 13-of-24 10.0 GB: 14-of-24 9.6 GB: 15-of-24 10.0 GB: 16-of-24 9.9 GB: 17-of-24 10.0 GB: 18-of-24 9.7 GB: 19-of-24 10.0 GB: 20-of-24 9.8 GB: 21-of-24 9.6 GB: 22-of-24 10.0 GB: 23-of-24 8.6 GB: 24-of-24
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Saily 100B 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 Saily 100B

Best Alternatives	Context / RAM	Downloads	Likes
SmollerLM2 100M Instruct Sft	8K / 0.3 GB	9	1
SmollerLM2 100M	8K / 0.2 GB	5	0
Stockmark 2 100B Instruct Beta	4K / 192.9 GB	13	12
Stockmark 100B	4K / 191.9 GB	9	34
Plankton 100M	4K / 0.4 GB	8	0
Webcoder 100M Html Css Js	2K / 0.4 GB	487	0
...Climbmix Dolmino Midtrain 100B	2K / 1.5 GB	450	0
...lisLM 100M Layer Hidden Pruned	2K / 0.2 GB	820	0
Reglu 100B	2K / 2.6 GB	7	1
Mossez 100M Coder Base	1K / 0.4 GB	113	0

Note: green Score (e.g. "73.2") means that the model is better than deepnight-research/saily_100b.