What are the hardware requirements for Fireball Mistral Nemo Base 2407 Sft V1?

Fireball Mistral Nemo Base 2407 Sft V1 requires approximately 24.5 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 Fireball Mistral Nemo Base 2407 Sft V1 and how large is it?

Fireball Mistral Nemo Base 2407 Sft V1 is developed by EpistemeAI, a model with 12.2b 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 Fireball Mistral Nemo Base 2407 Sft V1?

Fireball Mistral Nemo Base 2407 Sft V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Fireball Mistral Nemo Base 2407 Sft V1 by EpistemeAI — VRAM 24.5GB, 1000K context

Name: Fireball Mistral Nemo Base 2407 Sft V1
Author: EpistemeAI

Fireball Mistral Nemo Base 2407 Sft V1 is an open-source language model by EpistemeAI. Features: 12.2b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, Quantized, LLM Explorer Score: 0.14.

4bit Autotrain compatible Base model:finetune:unsloth/mi... Base model:unsloth/mistral-nem... Dataset:yahma/alpaca-cleaned En Endpoints compatible Mistral Quantized Region:us Safetensors Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v1

Fireball Mistral Nemo Base 2407 Sft V1 Parameters and Internals

LLM Name	Fireball Mistral Nemo Base 2407 Sft V1
Repository 🤗	https://huggingface.co/EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v1
Base Model(s)	...istral Nemo Base 2407 Bnb 4bit unsloth/Mistral-Nemo-Base-2407-bnb-4bit
Model Size	12.2b
Required VRAM	24.5 GB
Updated	2024-08-31
Maintainer	EpistemeAI
Model Type	mistral
Model Files	4.9 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 4.9 GB: 5-of-5
Supported Languages	en
Quantization Type	4bit
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.44.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Fireball Mistral Nemo Base 2407 Sft 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

Quantized Models of the Fireball Mistral Nemo Base 2407 Sft V1

Model	Likes	Downloads	VRAM
...Nemo Base 2407 Sft V2 F16 Gguf	0	8	24 GB

Best Alternatives to Fireball Mistral Nemo Base 2407 Sft V1

Best Alternatives	Context / RAM	Downloads	Likes
NemoR	1000K / 24.5 GB	24	0
Nemo Carpmuscle V0.1	1000K / 24.5 GB	4	1
...d 1.0 Nemo Base 2407 Ita 16bit	1000K / 24.5 GB	2579	4
NaturalLM	1000K / 24.5 GB	163	6
NaturalLM	1000K / 24.5 GB	27	6
...all MathMistral Nemo Base 2407	1000K / 24.5 GB	13	1
RAISED Mistral Nemo SFT	128K / 24.5 GB	12	0
Luca MN Bf16	128K / 24.5 GB	7	0
...aptain Eris Violet GRPO V0.420	1000K / 24.5 GB	23	24
...istral Nemo Instruct 2407 MPOA	1000K / 24.5 GB	37	3

Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v1.