What are the hardware requirements for MN 12B Tarsus?

MN 12B Tarsus requires approximately 24.6 GB of VRAM and supports a context window of 1000K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MN 12B Tarsus and how large is it?

MN 12B Tarsus is developed by Envoid, a model with 12b 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 MN 12B Tarsus?

MN 12B Tarsus is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MN 12B Tarsus by Envoid — VRAM 24.6GB, 1000K context

Name: MN 12B Tarsus
Author: Envoid

MN 12B Tarsus is an open-source language model by Envoid. Features: 12b LLM, VRAM: 24.6GB, Context: 1000K, License: cc-by-nc-2.0, Instruction-Based, LLM Explorer Score: 0.13.

Instruct Mistral Not-for-all-audiences Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Envoid/MN-12B-Tarsus

MN 12B Tarsus Parameters and Internals

Model Type

full-weight finetune

Use Cases

Applications:

chatting, roleplaying via SillyTavern

Limitations:

sometimes fumbles with tokens in odd places, imperfect for assistant capabilities

Additional Notes

- Reduce shiver-slop - More conversationally proactive - Less gratuitous purple prose - Reducing overall positivity bias

Training Details

Methodology:

Finetuned on a corpus that includes adult content

LLM Name	MN 12B Tarsus
Repository 🤗	https://huggingface.co/Envoid/MN-12B-Tarsus
Model Size	12b
Required VRAM	24.6 GB
Updated	2025-09-23
Maintainer	Envoid
Model Type	mistral
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-5 5.0 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 4.8 GB: 5-of-5
Model Architecture	MistralForCausalLM
License	cc-by-nc-2.0
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.44.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	131072
Torch Data Type	float16

Rank the MN 12B Tarsus 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 MN 12B Tarsus

Best Alternatives	Context / RAM	Downloads	Likes
...r Nemo 12B Instruct R 21 09 24	1000K / 24.5 GB	396277	141
Qliphoth 12B V1.1	1000K / 24.5 GB	22	3
Qliphoth 12B V1	1000K / 24.5 GB	26	2
SauerkrautLM Nemo 12B Instruct	1000K / 24.5 GB	1473	22
Magnum V4 12B	1000K / 24.5 GB	1116	54
MN Slush	1000K / 24.5 GB	181	32
ChatWaifu V1.4	1000K / 24.5 GB	335	20
...g M Claude Opus High Reasoning	1000K / 24.5 GB	126	3
ChatWaifu 12B V2.0	1000K / 24.5 GB	175	22
Mistral Nemo Bophades 12B	1000K / 24.5 GB	18	9

Note: green Score (e.g. "73.2") means that the model is better than Envoid/MN-12B-Tarsus.