What are the hardware requirements for Swallow Hermes St V1?

Swallow Hermes St V1 requires approximately 14.6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Swallow Hermes St V1 and how large is it?

Swallow Hermes St V1 is developed by napopoa32, a model with 7.3b 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 Swallow Hermes St V1?

Swallow Hermes St V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Swallow Hermes St V1 by napopoa32 — VRAM 14.6GB, 4K context

Name: Swallow Hermes St V1
Author: napopoa32

Swallow Hermes St V1 is an open-source language model by napopoa32. Features: 7.3b LLM, VRAM: 14.6GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.11.

Arxiv:2310.04799 Endpoints compatible Ja Mistral Region:us Safetensors Sharded Swallow Tensorflow

Model Card on HF 🤗: https://huggingface.co/napopoa32/swallow-hermes-st-v1

Swallow Hermes St V1 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

entertainment, story generation

Applications:

bedtime story generation

Primary Use Cases:

generating entertaining stories, creating bedtime stories

Limitations:

not optimized for factual content, may not produce intended emotional tone

Considerations:

The model aims to provide entertaining and engaging stories before sleep.

Additional Notes

This model is intended for creating engaging narratives but may produce unexpected tones.

Supported Languages

ja (Japanese)

Training Details

Methodology:

Based on Chat Vector and EvoLLM techniques with evolutionary strategy optimization.

Model Architecture:

Derived from Swallow-MS-7b-v0.1 with added vectors from Hermes-2-Pro-Mistral-7B and Mistral-7B-Instruct-v0.2-Neural-Story.

Input Output

Input Format:

Prompts with narrative or dialogue description

Accepted Modalities:

text

Output Format:

Generated narrative response

LLM Name	Swallow Hermes St V1
Repository 🤗	https://huggingface.co/napopoa32/swallow-hermes-st-v1
Model Size	7.3b
Required VRAM	14.6 GB
Updated	2026-07-08
Maintainer	napopoa32
Model Type	mistral
Model Files	4.9 GB: 1-of-3 4.9 GB: 2-of-3 4.8 GB: 3-of-3
Supported Languages	ja
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	42800
Torch Data Type	float16

Rank the Swallow Hermes St V1 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 Swallow Hermes St V1

Best Alternatives	Context / RAM	Downloads	Likes
Dictalm2.0 Instruct	32K / 14.5 GB	2791	25
My Tokenizer 100 10000	32K / 22.3 GB	12	0
My Tokenizer 50 20000	32K / 14.6 GB	7	0
Dictalm2.0	32K / 14.5 GB	368	28
Mis	32K / 14.6 GB	6	0
Dictalm2 It Qa Fine Tune	32K / 14.5 GB	26	7
Misjava Api 060924 V3 Merged	32K / 14.6 GB	5	0
... Fine Tuned Alpaca Gpt4 Hebrew	32K / 14.5 GB	201	0
Dictalm2.0 Instruct Fine Tuned	32K / 14.5 GB	21	0
Quietstar 8 Ahead	32K / 14.5 GB	43	90

Note: green Score (e.g. "73.2") means that the model is better than napopoa32/swallow-hermes-st-v1.