What are the hardware requirements for Sakaltum 7B?

Sakaltum 7B requires approximately 14.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sakaltum 7B and how large is it?

Sakaltum 7B is developed by sakaltcommunity, 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 Sakaltum 7B?

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

Sakaltum 7B by sakaltcommunity — VRAM 14.5GB, 32K context

Name: Sakaltum 7B
Author: sakaltcommunity

Sakaltum 7B is an open-source language model by sakaltcommunity. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: mit, Instruction-Based, Merged, LLM Explorer Score: 0.19.

Merged Model Arxiv:2306.01708 Base model:rakuten/rakutenai-7... Base model:sakanaai/evollm-jp-... Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/sakaltcommunity/sakaltum-7b

Sakaltum 7B Parameters and Internals

LLM Name	Sakaltum 7B
Repository 🤗	https://huggingface.co/sakaltcommunity/sakaltum-7b
Base Model(s)	EvoLLM JP A V1 7B RakutenAI 7B Instruct SakanaAI/EvoLLM-JP-A-v1-7B Rakuten/RakutenAI-7B-instruct
Merged Model	Yes
Model Size	7b
Required VRAM	14.5 GB
Updated	2026-07-01
Maintainer	sakaltcommunity
Model Type	mistral
Instruction-Based	Yes
Model Files	1.0 GB: 1-of-15 1.0 GB: 2-of-15 1.0 GB: 3-of-15 1.0 GB: 4-of-15 0.9 GB: 5-of-15 1.0 GB: 6-of-15 1.0 GB: 7-of-15 1.0 GB: 8-of-15 0.9 GB: 9-of-15 1.0 GB: 10-of-15 1.0 GB: 11-of-15 1.0 GB: 12-of-15 0.9 GB: 13-of-15 1.0 GB: 14-of-15 0.8 GB: 15-of-15
Model Architecture	MistralForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.45.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Sakaltum 7B 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 Sakaltum 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
... Summarize 64K QLoRANET Merged	128K / 4.1 GB	10	0
...1 Summarize 64K LoRANET Merged	128K / 14.4 GB	13	0
Mistral 7B Instruct V0.2	32K / 14.4 GB	1115337	3184
Mistral 7B Instruct V0.1	32K / 14.4 GB	253629	1846
Mistral 7B Instruct V0.2	32K / 14.4 GB	1338	0
Lexi Coder V5.1	32K / 14.5 GB	197	0

Note: green Score (e.g. "73.2") means that the model is better than sakaltcommunity/sakaltum-7b.