What are the hardware requirements for Stockmark 13B Instruct?

Stockmark 13B Instruct requires approximately 26.5 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Stockmark 13B Instruct and how large is it?

Stockmark 13B Instruct is developed by stockmark, a model with 13b 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 13B Instruct?

Stockmark 13B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Stockmark 13B Instruct by stockmark — VRAM 26.5GB, 2K context

Name: Stockmark 13B Instruct
Author: stockmark

Stockmark 13B Instruct is an open-source language model by stockmark. Features: 13b LLM, VRAM: 26.5GB, Context: 2K, License: mit, Instruction-Based, LLM Explorer Score: 0.09.

Deploy:azure Endpoints compatible Instruct Ja Japanese Llama Llama2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/stockmark/stockmark-13b-instruct

Stockmark 13B Instruct Parameters and Internals

Model Type

text-generation

Additional Notes

Instructions on use and implementation provided in the article/blog linked.

Supported Languages

jp (Japanese)

Training Details

Data Sources:

Project of Development of Japanese Instruction data for LLM

Methodology:

Instruction tuning

Input Output

Accepted Modalities:

text

LLM Name	Stockmark 13B Instruct
Repository 🤗	https://huggingface.co/stockmark/stockmark-13b-instruct
Model Size	13b
Required VRAM	26.5 GB
Updated	2026-07-30
Maintainer	stockmark
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.7 GB: 3-of-3
Supported Languages	ja
Model Architecture	LlamaForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.34.1
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	50000
Torch Data Type	bfloat16

Rank the Stockmark 13B Instruct 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 13B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
NexusRaven 13B	16K / 26 GB	37	106
Panda Coder 13B	16K / 26 GB	11	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	8	28
Gen Sim	16K / 0.3 GB	4	3
Llama 3 13B Instruct Ft	8K / 26.1 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than stockmark/stockmark-13b-instruct.