What are the hardware requirements for Lumimaid Magnum 12B EXL2 8.0?

Lumimaid Magnum 12B EXL2 8.0 requires approximately 12.6 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 Lumimaid Magnum 12B EXL2 8.0 and how large is it?

Lumimaid Magnum 12B EXL2 8.0 is developed by ParasiticRogue, 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 Lumimaid Magnum 12B EXL2 8.0?

Lumimaid Magnum 12B EXL2 8.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lumimaid Magnum 12B EXL2 8.0 by ParasiticRogue — VRAM 12.6GB, 1000K context

Name: Lumimaid Magnum 12B EXL2 8.0
Author: ParasiticRogue

Lumimaid Magnum 12B EXL2 8.0 is an open-source language model by ParasiticRogue. Features: 12b LLM, VRAM: 12.6GB, Context: 1000K, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

8-bit Autotrain compatible Base model:intervitens/mini-ma... Base model:merge:intervitens/m... Base model:merge:mistralai/mis... Base model:merge:neversleep/lu... Base model:merge:undi95/localc... Base model:mistralai/mistral-n... Base model:neversleep/lumimaid... Base model:undi95/localc-12b-e... Conversational Endpoints compatible Exl2 Instruct Merge Mergekit Mistral Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ParasiticRogue/Lumimaid-Magnum-12B-exl2-8.0

Lumimaid Magnum 12B EXL2 8.0 Parameters and Internals

LLM Name	Lumimaid Magnum 12B EXL2 8.0
Repository 🤗	https://huggingface.co/ParasiticRogue/Lumimaid-Magnum-12B-exl2-8.0
Base Model(s)	Mistral Nemo Instruct 2407 NeverSleep/Lumimaid-v0.2-12B Undi95/LocalC-12B-e2.0 intervitens/mini-magnum-12b-v1.1 mistralai/Mistral-Nemo-Instruct-2407 NeverSleep/Lumimaid-v0.2-12B Undi95/LocalC-12B-e2.0 intervitens/mini-magnum-12b-v1.1
Model Size	12b
Required VRAM	12.6 GB
Updated	2024-12-02
Maintainer	ParasiticRogue
Model Type	mistral
Instruction-Based	Yes
Model Files	4.2 GB: 1-of-3 4.3 GB: 2-of-3 4.1 GB: 3-of-3
Quantization Type	exl2
Model Architecture	MistralForCausalLM
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.44.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Lumimaid Magnum 12B EXL2 8.0 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 Lumimaid Magnum 12B EXL2 8.0

Best Alternatives	Context / RAM	Downloads	Likes
Geneva 12B GCv2 5M	1000K / 24.5 GB	29	13
ReWiz Nemo 12B Instruct	1000K / 24.5 GB	6	2
...o Instruct 12B Philosophy Math	1000K / 24.5 GB	17	1
...omix Unleashed 12B V0.6.1 8bit	1000K / 12.9 GB	4	2
Ava 1.0 12B	1000K / 24.5 GB	34	4
Poemma 12B	1000K / 24.5 GB	25	2
...t RP Noodles 12B V1.4 EXL2 8.0	1000K / 12.5 GB	34	2
DeepOpus 1 12B Preview	128K / 24.5 GB	18	0
DeepNeo 1 12B Preview	128K / 24.5 GB	15	0
...r Nemo 12B Instruct R 21 09 24	1000K / 24.5 GB	396277	141

Note: green Score (e.g. "73.2") means that the model is better than ParasiticRogue/Lumimaid-Magnum-12B-exl2-8.0.