What are the hardware requirements for Nomi 1.1?

Nomi 1.1 requires approximately 6.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nomi 1.1 and how large is it?

Nomi 1.1 is developed by JallyAI, a model with 3b 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 Nomi 1.1?

Nomi 1.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nomi 1.1 by JallyAI — VRAM 6.5GB

Name: Nomi 1.1
Author: JallyAI

Nomi 1.1 is an open-source language model by JallyAI. Features: 3b LLM, VRAM: 6.5GB, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.23.

Adapter Adapter-transformers Base model:adapter:jallyai/nom... Base model:jallyai/nomi-1.0-3b Codegen Conversational Dataset:magpie-align/magpie-ll... Dataset:magpie-align/magpie-pr... Dataset:magpie-align/magpie-qw... De Efficient En Finetuned Gguf Instruct Lazyloopstudio Llama Llama3 Lora Nomi Nomi1.1 Ollama Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/JallyAI/Nomi-1.1

Nomi 1.1 Parameters and Internals

LLM Name	Nomi 1.1
Repository 🤗	https://huggingface.co/JallyAI/Nomi-1.1
Base Model(s)	LL-Nomi-AI/Nomi-1.0-3b LL-Nomi-AI/Nomi-1.0-3b
Model Size	3b
Required VRAM	6.5 GB
Updated	2026-07-26
Maintainer	JallyAI
Instruction-Based	Yes
Model Files	0.2 GB 5.0 GB: 1-of-2 1.5 GB: 2-of-2 0.0 GB
Supported Languages	de en
Generates Code	Yes
Model Architecture	Adapter
License	apache-2.0
Model Max Length	131072
Is Biased	none
Tokenizer Class	TokenizersBackend
Padding Token	<\|finetune_right_pad_id\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|up_proj\|q_proj\|gate_proj\|down_proj\|o_proj\|k_proj
LoRA Alpha	32
LoRA Dropout	0
R Param	32

Rank the Nomi 1.1 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 Nomi 1.1

Best Alternatives	Context / RAM	Downloads	Likes
Cc Coder	0K / 0.1 GB	24	0

Note: green Score (e.g. "73.2") means that the model is better than JallyAI/Nomi-1.1.