What are the hardware requirements for Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K?

Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K requires approximately 3.4 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Where can I download or evaluate Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K?

Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K by ali-elganzory — VRAM 3.4GB, 16K context

Name: Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K
Author: ali-elganzory

Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K is an open-source language model by ali-elganzory. Features: 300b LLM, VRAM: 3.4GB, Context: 16K, License: other, LLM Explorer Score: 0.23.

Base model:finetune:open-sci/o... Base model:open-sci/open-sci-r... Conversational Custom code Full Generated from trainer Llama-factory Opensci Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/ali-elganzory/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096-4096-longsft_16k

Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K Parameters and Internals

LLM Name	Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16k
Repository 🤗	https://huggingface.co/ali-elganzory/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096-4096-longsft_16k
Base Model(s)	open-sci/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096 open-sci/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096
Model Size	300b
Required VRAM	3.4 GB
Updated	2026-07-22
Maintainer	ali-elganzory
Model Type	opensci
Model Files	3.4 GB
Model Architecture	OpensciForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.51.3
Tokenizer Class	GPTNeoXTokenizer
Padding Token	<end_of_turn>
Vocabulary Size	50304
Torch Data Type	bfloat16

Rank the Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K 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 Open Sci Ref V0.02 1.7B Fineweb Edu 1.4t 300B 4096 4096 Longsft 16K

Best Alternatives	Context / RAM	Downloads
...t 16k SFT Tulu3 Decontaminated	16K / 3.4 GB	278
...Longsft 16k SFT Tulu3 Decontam	16K / 3.4 GB	272
...t 16k SFT Tulu3 Decontaminated	16K / 3.4 GB	271
...easoning 300B 4096 Longsft 16k	16K / 3.4 GB	39
...urevitae 300B 4096 Longsft 16k	16K / 3.4 GB	37
...easoning 300B 4096 Longsft 16k	16K / 3.4 GB	35
...instruct 300B 4096 Longsft 16k	16K / 3.4 GB	30
...otron Hq 300B 4096 Longsft 16k	16K / 3.4 GB	29
...t 16k SFT Tulu3 Decontaminated	16K / 3.4 GB	11
....7B Dclm 300B 4096 Longsft 16k	16K / 3.4 GB	13

Note: green Score (e.g. "73.2") means that the model is better than ali-elganzory/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096-4096-longsft_16k.