“They are against the Machine?” “They would be against mathematics or against the art of writing if they had lived at the appropriate time.” > — Isaac Asimov, I, Robot (1950)

🌑 About Neural

Neural is a Mistral Small (24B) model for narrative generation and roleplay. This repo is for the GGUF version of NeuR0mancR/Neural-v1-24B and its quants.

🛠 Technical Specifications

Base Architecture: Mistral Small 3.2 (24B)
Chat Template: Mistral Tekken
Primary Focus: Narrative weight, structural integrity, and stylistic "grit."

About

These are static and weighted/imatrix quants of NeuR0mancR/Neural-v1-24B

The IQ-quants were calibrated with a custom importance matrix to stay in line with the model's intended theme. Feel free to requantize with your own if you desire to preserve a different set of weights. The imatrix file used is included in this repo. IQ quants are recommended over similar sized non-IQ quantization.

Feel free to share your feedbacks.

Note: The IQ3_M_ATTN had its embedding, output and attention weights preserved at Q6_K. It is a decent compromise in a memory starved environment.

Downloads last month: 176

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for NeuR0mancR/Neural-v1-24B-GGUF

Base model

NeuR0mancR/Neural-v1-24B

Quantized

(3)

this model