What are the hardware requirements for Canidori 12B V1?

Canidori 12B V1 requires approximately 23.8 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 Canidori 12B V1 and how large is it?

Canidori 12B V1 is developed by GalrionSoftworks, 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 Canidori 12B V1?

Canidori 12B V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Canidori 12B V1 by GalrionSoftworks — VRAM 23.8GB, 1000K context

Name: Canidori 12B V1
Author: GalrionSoftworks

Canidori 12B V1 is an open-source language model by GalrionSoftworks. Features: 12b LLM, VRAM: 23.8GB, Context: 1000K, Merged, LLM Explorer Score: 0.14.

Merged Model Aetherwiing/mn-12b-starcannon-... Base model:crestf411/nemo-sunf... Base model:nothingiisreal/mn-1... Crestf411/nemo-sunfall-v0.6.1 Mistral Nothingiisreal/mn-12b-celeste-... Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/GalrionSoftworks/Canidori-12B-v1

Canidori 12B V1 Parameters and Internals

Model Type

text generation

Additional Notes

Canidori-12B-v1 is a merged model using LazyMergekit from three different models: nothingiisreal/MN-12B-Celeste-V1.9, crestf411/nemo-sunfall-v0.6.1, and base model aetherwiing/MN-12B-Starcannon-v3.

Input Output

Input Format:

{'role': 'user', 'content': 'Your question here'}

Accepted Modalities:

text

Output Format:

generated_text

LLM Name	Canidori 12B V1
Repository 🤗	https://huggingface.co/GalrionSoftworks/Canidori-12B-v1
Base Model(s)	nothingiisreal/MN-12B-Celeste-V1.9 crestf411/nemo-sunfall-v0.6.1 nothingiisreal/MN-12B-Celeste-V1.9 crestf411/nemo-sunfall-v0.6.1
Merged Model	Yes
Model Size	12b
Required VRAM	23.8 GB
Updated	2026-08-02
Maintainer	GalrionSoftworks
Model Type	mistral
Model Files	1.3 GB: 1-of-25 1.3 GB: 2-of-25 1.0 GB: 3-of-25 0.9 GB: 4-of-25 0.9 GB: 5-of-25 0.9 GB: 6-of-25 1.0 GB: 7-of-25 0.9 GB: 8-of-25 0.9 GB: 9-of-25 0.9 GB: 10-of-25 1.0 GB: 11-of-25 0.9 GB: 12-of-25 0.9 GB: 13-of-25 0.9 GB: 14-of-25 1.0 GB: 15-of-25 0.9 GB: 16-of-25 0.9 GB: 17-of-25 0.9 GB: 18-of-25 1.0 GB: 19-of-25 0.9 GB: 20-of-25 0.9 GB: 21-of-25 0.9 GB: 22-of-25 1.0 GB: 23-of-25 0.9 GB: 24-of-25 0.8 GB: 25-of-25
Model Architecture	MistralForCausalLM
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.44.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Canidori 12B 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 Canidori 12B V1

Best Alternatives	Context / RAM	Downloads	Likes
...r Nemo 12B Instruct R 21 09 24	1000K / 24.5 GB	396277	141
MN 12B Mag Mell R1	1000K / 24.5 GB	69558	238
Riverfish Rocinante 12B SFT	1000K / 49.4 GB	166	1
Riverfish Rocinante 12B	1000K / 49.4 GB	111	1
MN 12B LucidFaun RP RU	1000K / 24.5 GB	1005	6
Qliphoth 12B V1.2	1000K / 24.5 GB	107	7
Captain Eris BMO Violent 12B	1000K / 24.5 GB	305	2
Shining Gold Sakura 12B	1000K / 24.5 GB	52	2
Dans SakuraKaze V1.0.0 12B	1000K / 24.5 GB	7	21
...n Eris BMO Violent GRPO V0.420	1000K / 24.5 GB	92	3

Note: green Score (e.g. "73.2") means that the model is better than GalrionSoftworks/Canidori-12B-v1.