What are the hardware requirements for SJT 7B V1.1 Multilingal?

SJT 7B V1.1 Multilingal requires approximately 16.2 GB of VRAM and supports a context window of 986K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SJT 7B V1.1 Multilingal and how large is it?

SJT 7B V1.1 Multilingal is developed by Sakalti, a model with 7b 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 SJT 7B V1.1 Multilingal?

SJT 7B V1.1 Multilingal is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SJT 7B V1.1 Multilingal by Sakalti — VRAM 16.2GB, 986K context

Name: SJT 7B V1.1 Multilingal
Author: Sakalti

SJT 7B V1.1 Multilingal is an open-source language model by Sakalti. Features: 7b LLM, VRAM: 16.2GB, Context: 986K, Merged, LLM Explorer Score: 0.18.

Merged Model Arxiv:2306.01708 Base model:lightblue/deepseek-... Base model:sakalti/sjt-7b-v1.1 Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Sakalti/SJT-7B-V1.1-Multilingal

SJT 7B V1.1 Multilingal Parameters and Internals

LLM Name	SJT 7B V1.1 Multilingal
Repository 🤗	https://huggingface.co/Sakalti/SJT-7B-V1.1-Multilingal
Base Model(s)	...1 Distill Qwen 7B Multilingual Sakalti/SJT-7B-V1.1 lightblue/DeepSeek-R1-Distill-Qwen-7B-Multilingual Sakalti/SJT-7B-V1.1
Merged Model	Yes
Model Size	7b
Required VRAM	16.2 GB
Updated	2026-05-13
Maintainer	Sakalti
Model Type	qwen2
Model Files	1.1 GB: 1-of-30 1.1 GB: 2-of-30 0.5 GB: 3-of-30 0.5 GB: 4-of-30 0.5 GB: 5-of-30 0.5 GB: 6-of-30 0.5 GB: 7-of-30 0.5 GB: 8-of-30 0.5 GB: 9-of-30 0.5 GB: 10-of-30 0.5 GB: 11-of-30 0.5 GB: 12-of-30 0.5 GB: 13-of-30 0.5 GB: 14-of-30 0.5 GB: 15-of-30 0.5 GB: 16-of-30 0.5 GB: 17-of-30 0.5 GB: 18-of-30 0.5 GB: 19-of-30 0.5 GB: 20-of-30 0.5 GB: 21-of-30 0.5 GB: 22-of-30 0.5 GB: 23-of-30 0.5 GB: 24-of-30 0.5 GB: 25-of-30 0.5 GB: 26-of-30 0.5 GB: 27-of-30 0.5 GB: 28-of-30 0.5 GB: 29-of-30 0.5 GB: 30-of-30
Model Architecture	Qwen2ForCausalLM
Context Length	1010000
Model Max Length	1010000
Transformers Version	4.46.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151665
Torch Data Type	float16
Errors	replace

Rank the SJT 7B V1.1 Multilingal 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 SJT 7B V1.1 Multilingal

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 7B Preview	986K / 15.2 GB	10	0
Qwen2.5 7B Instruct 1M	986K / 15.4 GB	52534	373
Hush Qwen2.5 7B V1.2	986K / 15.2 GB	4	1
Hush Qwen2.5 7B V1.1	986K / 15.2 GB	5	1
Hush Qwen2.5 7B V1.4	986K / 15.2 GB	8	1
Hush Qwen2.5 7B Preview	986K / 15.2 GB	5	0
Hush Qwen2.5 7B V1.3	986K / 15.2 GB	10	2
Hush Qwen2.5 7B RP V1.4 1M	986K / 15.2 GB	10	2
Qwen 2.5 7B Exp Sce	986K / 15.2 GB	10	2
Qwen2.5 7B MixStock V0.1	986K / 15.2 GB	6	3

Note: green Score (e.g. "73.2") means that the model is better than Sakalti/SJT-7B-V1.1-Multilingal.