What are the hardware requirements for MN Magnum V2.5 18.5B Kto Instruct?

MN Magnum V2.5 18.5B Kto Instruct requires approximately 36.2 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 Magnum V2.5 18.5B Kto Instruct and how large is it?

MN Magnum V2.5 18.5B Kto Instruct is developed by DavidAU, 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 Magnum V2.5 18.5B Kto Instruct?

MN Magnum V2.5 18.5B Kto Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MN Magnum V2.5 18.5B Kto Instruct by DavidAU — VRAM 36.2GB, 1000K context

Name: MN Magnum V2.5 18.5B Kto Instruct
Author: DavidAU

MN Magnum V2.5 18.5B Kto Instruct is an open-source language model by DavidAU. Features: 12b LLM, VRAM: 36.2GB, Context: 1000K, Instruction-Based, Merged, LLM Explorer Score: 0.14.

Merged Model Autotrain compatible Conversational Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct

MN Magnum V2.5 18.5B Kto Instruct Parameters and Internals

Additional Notes

This model is a merge of pre-trained language models created using mergekit with the passthrough merge method.

LLM Name	MN Magnum V2.5 18.5B Kto Instruct
Repository 🤗	https://huggingface.co/DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct
Merged Model	Yes
Model Size	12b
Required VRAM	36.2 GB
Updated	2025-09-23
Maintainer	DavidAU
Model Type	mistral
Instruction-Based	Yes
Model Files	1.3 GB: 1-of-38 1.3 GB: 2-of-38 1.0 GB: 3-of-38 1.0 GB: 4-of-38 0.9 GB: 5-of-38 0.9 GB: 6-of-38 0.9 GB: 7-of-38 0.9 GB: 8-of-38 0.9 GB: 9-of-38 0.9 GB: 10-of-38 1.0 GB: 11-of-38 1.0 GB: 12-of-38 0.9 GB: 13-of-38 0.9 GB: 14-of-38 1.0 GB: 15-of-38 1.0 GB: 16-of-38 0.9 GB: 17-of-38 0.9 GB: 18-of-38 0.9 GB: 19-of-38 0.9 GB: 20-of-38 0.9 GB: 21-of-38 0.9 GB: 22-of-38 1.0 GB: 23-of-38 1.0 GB: 24-of-38 0.9 GB: 25-of-38 0.9 GB: 26-of-38 1.0 GB: 27-of-38 1.0 GB: 28-of-38 1.0 GB: 29-of-38 0.9 GB: 30-of-38 0.9 GB: 31-of-38 1.0 GB: 32-of-38 0.9 GB: 33-of-38 0.9 GB: 34-of-38 0.9 GB: 35-of-38 1.0 GB: 36-of-38 0.9 GB: 37-of-38 0.8 GB: 38-of-38
Model Architecture	MistralForCausalLM
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.43.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the MN Magnum V2.5 18.5B Kto Instruct 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 Magnum V2.5 18.5B Kto Instruct

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
...g M Claude Opus High Reasoning	1000K / 24.5 GB	82	3
ChatWaifu V1.4	1000K / 24.5 GB	335	20
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 DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct.