What are the hardware requirements for Stockmark 2 100B Instruct Beta?

Stockmark 2 100B Instruct Beta requires approximately 192.9 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 Stockmark 2 100B Instruct Beta and how large is it?

Stockmark 2 100B Instruct Beta is developed by stockmark, 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 Stockmark 2 100B Instruct Beta?

Stockmark 2 100B Instruct Beta is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Stockmark 2 100B Instruct Beta by stockmark — VRAM 192.9GB, 4K context

Name: Stockmark 2 100B Instruct Beta
Author: stockmark

Stockmark 2 100B Instruct Beta is an open-source language model by stockmark. Features: 100b LLM, VRAM: 192.9GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.17.

Conversational En Endpoints compatible Instruct Ja Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/stockmark/Stockmark-2-100B-Instruct-beta

Stockmark 2 100B Instruct Beta Parameters and Internals

LLM Name	Stockmark 2 100B Instruct Beta
Repository 🤗	https://huggingface.co/stockmark/Stockmark-2-100B-Instruct-beta
Model Size	100b
Required VRAM	192.9 GB
Updated	2026-07-20
Maintainer	stockmark
Model Type	llama
Instruction-Based	Yes
Model Files	4.4 GB: 1-of-40 5.0 GB: 2-of-40 5.0 GB: 3-of-40 5.0 GB: 4-of-40 4.8 GB: 5-of-40 5.0 GB: 6-of-40 5.0 GB: 7-of-40 5.0 GB: 8-of-40 4.8 GB: 9-of-40 5.0 GB: 10-of-40 5.0 GB: 11-of-40 5.0 GB: 12-of-40 4.8 GB: 13-of-40 5.0 GB: 14-of-40 5.0 GB: 15-of-40 5.0 GB: 16-of-40 4.8 GB: 17-of-40 5.0 GB: 18-of-40 5.0 GB: 19-of-40 5.0 GB: 20-of-40 4.8 GB: 21-of-40 5.0 GB: 22-of-40 5.0 GB: 23-of-40 5.0 GB: 24-of-40 4.8 GB: 25-of-40 5.0 GB: 26-of-40 5.0 GB: 27-of-40 5.0 GB: 28-of-40 4.8 GB: 29-of-40 5.0 GB: 30-of-40 5.0 GB: 31-of-40 5.0 GB: 32-of-40 4.8 GB: 33-of-40 5.0 GB: 34-of-40 5.0 GB: 35-of-40 5.0 GB: 36-of-40 4.8 GB: 37-of-40 5.0 GB: 38-of-40 3.4 GB: 39-of-40 1.9 GB: 40-of-40
Supported Languages	ja en
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.48.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Stockmark 2 100B Instruct Beta 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 Stockmark 2 100B Instruct Beta

Best Alternatives	Context / RAM	Downloads	Likes
SmollerLM2 100M Instruct Sft	8K / 0.3 GB	9	1
Mossez 100M Coder Instruct	1K / 0.4 GB	113	0

Note: green Score (e.g. "73.2") means that the model is better than stockmark/Stockmark-2-100B-Instruct-beta.