What are the hardware requirements for Pretraining Priors D26 Sft?

Pretraining Priors D26 Sft requires approximately 1.9 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 Pretraining Priors D26 Sft and how large is it?

Pretraining Priors D26 Sft is developed by jkminder, a model with 972.9m 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 Pretraining Priors D26 Sft?

Pretraining Priors D26 Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Pretraining Priors D26 Sft by jkminder — VRAM 1.9GB, 2K context

Name: Pretraining Priors D26 Sft
Author: jkminder

Pretraining Priors D26 Sft is an open-source language model by jkminder. Features: 972.9m LLM, VRAM: 1.9GB, Context: 2K, License: cc-by-nc-4.0, LLM Explorer Score: 0.31.

Arxiv:2504.13161 Base model:finetune:jkminder/p... Base model:jkminder/pretrainin... Chat Conversational Custom code Dataset:cais/mmlu Dataset:huggingfacetb/smol-smo... Dataset:nvidia/climbmix Dataset:openai/gsm8k En Nanochat Nanochat gpt Region:us Research Safetensors Sft

Model Card on HF 🤗: https://huggingface.co/jkminder/pretraining-priors-d26-sft

Pretraining Priors D26 Sft Parameters and Internals

LLM Name	Pretraining Priors D26 Sft
Repository 🤗	https://huggingface.co/jkminder/pretraining-priors-d26-sft
Base Model(s)	Pretraining Priors D26 Base jkminder/pretraining-priors-d26-base
Model Size	972.9m
Required VRAM	1.9 GB
Updated	2026-08-11
Maintainer	jkminder
Model Type	nanochat_gpt
Model Files	1.9 GB
Supported Languages	en
Model Architecture	NanochatGPTForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	5.14.1
Tokenizer Class	TokenizersBackend
Vocabulary Size	32768

Rank the Pretraining Priors D26 Sft 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 Pretraining Priors D26 Sft

Best Alternatives	Context / RAM	Downloads	Likes
...training Priors D26 Sft Numtox	2K / 1.9 GB	258	0
Pretraining Priors D26 Base	2K / 1.9 GB	63	0