What are the hardware requirements for Felix 8B?

Felix 8B requires approximately 17.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Felix 8B and how large is it?

Felix 8B is developed by ontocord, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Felix 8B perform on standard benchmarks?

Felix 8B has the following published scores: MMLU 61.05. Compare against reference models on this page or on the LLM Explorer leaderboards.

Felix 8B by ontocord — VRAM 17.9GB, 32K context

Name: Felix 8B
Author: ontocord

Felix 8B is an open-source language model by ontocord. Features: 8b LLM, VRAM: 17.9GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.13, Arc: 65, HellaSwag: 84.6, MMLU: 61.1, GSM8K: 51.8.

Conversational En Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ontocord/Felix-8B

Felix 8B Parameters and Internals

Model Type

language model

Additional Notes

Felix-8B is experimental and of a research work product with a strong focus on safety and truthfulness.

Supported Languages

en (English)

Training Details

Data Sources:

ontocord/sft-4e-exp2, OpenHermes 2.5 dataset

Methodology:

auto-purpleteaming

Responsible Ai Considerations

Fairness:

Efforts to mitigate potential biases during the training process.

Mitigation Strategies:

Designed with principles of lawfulness and equal access.

LLM Name	Felix 8B
Repository 🤗	https://huggingface.co/ontocord/Felix-8B
Model Size	8b
Required VRAM	17.9 GB
Updated	2026-08-04
Maintainer	ontocord
Model Type	mistral
Model Files	4.9 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 3.1 GB: 4-of-4 0.0 GB
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.1
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32002
Torch Data Type	bfloat16

Rank the Felix 8B 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 Felix 8B

Best Alternatives	Context / RAM	Downloads	Likes
Ministral 8B Instruct 2410 HF	32K / 32 GB	21	12
Ministrations 8B V1	32K / 16.1 GB	20	29
Minerva 8B	32K / 14.5 GB	7	0
...l 8B Instruct 2410 Abliterated	32K / 16.1 GB	46	3
Ministral 8B Slerp	32K / 29.2 GB	7	0
The Omega Directive M 8B V1.0	32K / 16.1 GB	30	9
Mistral Pro 8B V0.1	32K / 17.9 GB	83	67
Deeplm Mistral V0.1 8B Stage1	32K / 14.5 GB	16	1
Forgotten Abomination 8B V2.2	32K / 16.1 GB	11	2
Forgotten Safeword 8B V2.2	32K / 16.1 GB	4	1

Note: green Score (e.g. "73.2") means that the model is better than ontocord/Felix-8B.