What are the hardware requirements for Norn V15?

Norn V15 requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Norn V15 and how large is it?

Norn V15 is developed by Osakra, a model with 4b 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 Norn V15?

Norn V15 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Norn V15 by Osakra — VRAM 0.1GB

Name: Norn V15
Author: Osakra

Norn V15 is an open-source language model by Osakra. Features: 4b LLM, VRAM: 0.1GB, License: apache-2.0, LLM Explorer Score: 0.25.

Arxiv:2110.14168 Arxiv:2207.10342 Adapter Agentic Base model:adapter:qwen/qwen3-... Base model:qwen/qwen3-4b-base Code Continuous-latent-cot En Finetuned Holographic-memory Lora Ltc-ode Math Neuro-symbolic Osakra-research Peft Qwen3 Reasoning Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Osakra/norn-v15

Norn V15 Parameters and Internals

LLM Name	Norn V15
Repository 🤗	https://huggingface.co/Osakra/norn-v15
Base Model(s)	Qwen3 4B Base Qwen/Qwen3-4B-Base
Model Size	4b
Required VRAM	0.1 GB
Updated	2026-09-08
Maintainer	Osakra
Model Files	0.1 GB 0.0 GB
Supported Languages	en
Model Architecture	Adapter
License	apache-2.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	down_proj\|k_proj\|v_proj\|gate_proj\|q_proj\|up_proj\|o_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Norn V15 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 Norn V15

Best Alternatives	Context / RAM	Downloads	Likes
Kev 4B	0K / 0.1 GB	16100	101
Qwen Las V0.1	0K / 0 GB	6	0
MathFT4B	0K / 0 GB	232	1
...chet Nemotron Nano 4B Text2sql	0K / 0 GB	67	2
Qwen3.5 4B Steering Oracle	0K / 0 GB	38	1
Visual Jev 4B Answer Sft	0K / 0.1 GB	466	2
PathJev P	0K / 0.2 GB	34	2
Ephedra 0.5 Cyber Experimental	0K / 0.3 GB	24	0
Text2SQL 4B Model	0K / 0.3 GB	22	1
Diapason	0K / 0.1 GB	31	1

Note: green Score (e.g. "73.2") means that the model is better than Osakra/norn-v15.