What are the hardware requirements for Normistral 11B Thinking?

Normistral 11B Thinking requires approximately 22.8 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 Normistral 11B Thinking and how large is it?

Normistral 11B Thinking is developed by ltg, a model with 11b 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 Normistral 11B Thinking?

Normistral 11B Thinking is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Normistral 11B Thinking by ltg — VRAM 22.8GB, 1000K context

Name: Normistral 11B Thinking
Author: ltg

Normistral 11B Thinking is an open-source language model by ltg. Features: 11b LLM, VRAM: 22.8GB, Context: 1000K, License: apache-2.0, LLM Explorer Score: 0.21.

Arxiv:2504.07749 Arxiv:2512.08777 Base model:finetune:norallm/no... Base model:norallm/normistral-... Bokmaal Conversational Endpoints compatible Mistral Nb Nn No Norwegian Nynorsk Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ltg/normistral-11b-thinking

Normistral 11B Thinking Parameters and Internals

LLM Name	Normistral 11B Thinking
Repository 🤗	https://huggingface.co/ltg/normistral-11b-thinking
Base Model(s)	norallm/normistral-11b-long norallm/normistral-11b-long
Model Size	11b
Required VRAM	22.8 GB
Updated	2026-10-10
Maintainer	ltg
Model Type	mistral
Model Files	5.0 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 3.1 GB: 5-of-5
Supported Languages	nb nn no
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.55.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	51200
Torch Data Type	bfloat16

Rank the Normistral 11B Thinking 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 Normistral 11B Thinking

Best Alternatives	Context / RAM	Downloads	Likes
Starling LM 11B Alpha	32K / 21.4 GB	82	15
...elik V2.3 Instruct MedIT Merge	32K / 22.3 GB	1592	2
Normistral 11B Translate	32K / 22.8 GB	193	1
ConfigurableBeagle 11B	32K / 21.4 GB	8206	3
CarbonBeagle 11B	32K / 21.4 GB	8331	9
...elik V2.3 Instruct Llama Prune	32K / 15.4 GB	1387	0
CarbonBeagle 11B Truthy	32K / 21.4 GB	7713	10
MistralLite 11B	32K / 21.4 GB	1337	2
Mistral 11B Instruct V0.1	32K / 42.9 GB	169	2
Mistral Evolved 11B V0.1	32K / 22.3 GB	58	33

Note: green Score (e.g. "73.2") means that the model is better than ltg/normistral-11b-thinking.