What are the hardware requirements for Riverfish Rocinante 12B?

Riverfish Rocinante 12B requires approximately 49.4 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 Riverfish Rocinante 12B and how large is it?

Riverfish Rocinante 12B is developed by amylynn, 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 Riverfish Rocinante 12B?

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

Riverfish Rocinante 12B by amylynn — VRAM 49.4GB, 1000K context

Name: Riverfish Rocinante 12B
Author: amylynn

Riverfish Rocinante 12B is an open-source language model by amylynn. Features: 12b LLM, VRAM: 49.4GB, Context: 1000K, License: apache-2.0, Merged, LLM Explorer Score: 0.27.

Merged Model Base model:thedrummer/rivermin... Base model:thedrummer/rocinant... Base model:thedrummer/rocinant... Base model:thedrummer/rocinant... Base model:thedrummer/unslopne... Mistral Region:us Safetensors Sharded Tensorflow Thedrummer/rivermind-lux-12b-v... Thedrummer/rocinante-12b-v1 Thedrummer/rocinante-12b-v1.1 Thedrummer/rocinante-x-12b-v1 Thedrummer/unslopnemo-12b-v4.1

Model Card on HF 🤗: https://huggingface.co/amylynn/Riverfish-Rocinante-12B

Riverfish Rocinante 12B Parameters and Internals

LLM Name	Riverfish Rocinante 12B
Repository 🤗	https://huggingface.co/amylynn/Riverfish-Rocinante-12B
Base Model(s)	Rocinante 12B V1 TheDrummer/Rocinante-12B-v1.1 Rocinante X 12B V1 TheDrummer/UnslopNemo-12B-v4.1 Rivermind Lux 12B V1 TheDrummer/Rocinante-12B-v1 TheDrummer/Rocinante-12B-v1.1 TheDrummer/Rocinante-X-12B-v1 TheDrummer/UnslopNemo-12B-v4.1 TheDrummer/Rivermind-Lux-12B-v1
Merged Model	Yes
Model Size	12b
Required VRAM	49.4 GB
Updated	2026-08-04
Maintainer	amylynn
Model Type	mistral
Model Files	2.7 GB: 1-of-11 4.9 GB: 2-of-11 5.0 GB: 3-of-11 4.9 GB: 4-of-11 5.0 GB: 5-of-11 4.9 GB: 6-of-11 5.0 GB: 7-of-11 4.9 GB: 8-of-11 5.0 GB: 9-of-11 4.9 GB: 10-of-11 2.2 GB: 11-of-11
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	1024000
Model Max Length	1024000
Transformers Version	5.12.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072

Rank the Riverfish Rocinante 12B 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 Riverfish Rocinante 12B

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
MN 12B LucidFaun RP RU	1000K / 24.5 GB	1005	6
Qliphoth 12B V1.2	1000K / 24.5 GB	107	7
Shining Gold Sakura 12B	1000K / 24.5 GB	52	2
Captain Eris BMO Violent 12B	1000K / 24.5 GB	305	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
Mistral Nemo Kartoffel 12B	1000K / 24.5 GB	47	6

Note: green Score (e.g. "73.2") means that the model is better than amylynn/Riverfish-Rocinante-12B.