---
title: "Noema models"
description: "Every released Noema model with its Hugging Face repository, parameters, base model, formats, license and release date."
version: "Noema 1.5 · Noema 2B"
applies_to: "Hugging Face · NoemaAI-labs"
reviewed: "2026-10-23"
canonical: "https://noemaai.com/docs/models"
---

# Noema models

Every released Noema model with its repository, size, base model, formats, license and release date.

NoemaAI post-trains small language models from Qwen bases and publishes them on [Hugging Face](https://huggingface.co/NoemaAI-labs). This reference is generated from the same data as the [model pages](https://noemaai.com/models).

## Released models

| Model | Repository | Size | Base model | Formats | Released |
| --- | --- | --- | --- | --- | --- |
| [Noema 1.5 4B Deep](https://noemaai.com/models/noema-1-5-4b#deep) | [Noema-1.5-4B-Deep](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep) | 4B | Qwen3.5-4B | Transformers, GGUF, MLX (BF16, 8-bit, 6-bit, 4-bit) | Oct 13, 2026 |
| [Noema 1.5 4B Fast](https://noemaai.com/models/noema-1-5-4b#fast) | [Noema-1.5-4B-Fast](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast) | 4B | Qwen3.5-4B | Transformers, GGUF, MLX (BF16, 8-bit, 6-bit, 4-bit) | Oct 13, 2026 |
| [Noema 1.5 2B](https://noemaai.com/models/noema-1-5-2b) | [Noema-1.5-2B](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B) | 2B | Noema 2B, trained from Qwen3.5-2B | Transformers, GGUF, MLX (BF16, 8-bit, 6-bit, 4-bit) | Aug 12, 2026 |
| [Noema 2B](https://noemaai.com/models/noema-2b) | [Noema-2B](https://huggingface.co/NoemaAI-labs/Noema-2B) | 2B | Qwen3.5-2B | Transformers, GGUF | Jul 6, 2026 |

Noema 2B is deprecated; use Noema 1.5 2B instead. Its weights stay available.

Every Noema release is open weights, not open source. See [Model licenses](https://noemaai.com/docs/model-licenses) for the terms of each release.

## Context, modes and formats

| Model | Context | Modes | Formats |
| --- | --- | --- | --- |
| [Noema 1.5 4B](https://noemaai.com/models/noema-1-5-4b) | 262,144 tokens (architecture limit); outputs evaluated to 81,920 | Thinking (default) · non-thinking, selected through the chat template | SafeTensors (BF16) · GGUF (BF16 to Q4_K_M) · MLX (BF16 to 4-bit) |
| [Noema 1.5 2B](https://noemaai.com/models/noema-1-5-2b) | 262,144 tokens (architecture limit); independently validated to 24,576 | Non-thinking (recommended) · thinking | SafeTensors (BF16) · GGUF (BF16 to Q4_K_M) · MLX (BF16 to 4-bit) |
| [Noema 2B](https://noemaai.com/models/noema-2b) | 262,144 tokens (architecture limit) | Non-thinking (trained and evaluated); thinking mode is not supported | SafeTensors (BF16) · GGUF (F16 to Q4_K_M) |

A model's context limit is not a promise that it fits in your device's memory. Size the context to the work and the hardware.

## Repositories by format

| Model | Format | Repository |
| --- | --- | --- |
| Noema 1.5 4B Deep | Transformers | [NoemaAI-labs/Noema-1.5-4B-Deep](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep) |
| Noema 1.5 4B Deep | GGUF | [NoemaAI-labs/Noema-1.5-4B-Deep-GGUF](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep-GGUF) |
| Noema 1.5 4B Deep | MLX BF16 | [NoemaAI-labs/Noema-1.5-4B-Deep-MLX-BF16](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep-MLX-BF16) |
| Noema 1.5 4B Deep | MLX 8-bit | [NoemaAI-labs/Noema-1.5-4B-Deep-MLX-8bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep-MLX-8bit) |
| Noema 1.5 4B Deep | MLX 6-bit | [NoemaAI-labs/Noema-1.5-4B-Deep-MLX-6bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep-MLX-6bit) |
| Noema 1.5 4B Deep | MLX 4-bit | [NoemaAI-labs/Noema-1.5-4B-Deep-MLX-4bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Deep-MLX-4bit) |
| Noema 1.5 4B Fast | Transformers | [NoemaAI-labs/Noema-1.5-4B-Fast](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast) |
| Noema 1.5 4B Fast | GGUF | [NoemaAI-labs/Noema-1.5-4B-Fast-GGUF](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast-GGUF) |
| Noema 1.5 4B Fast | MLX BF16 | [NoemaAI-labs/Noema-1.5-4B-Fast-MLX-BF16](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast-MLX-BF16) |
| Noema 1.5 4B Fast | MLX 8-bit | [NoemaAI-labs/Noema-1.5-4B-Fast-MLX-8bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast-MLX-8bit) |
| Noema 1.5 4B Fast | MLX 6-bit | [NoemaAI-labs/Noema-1.5-4B-Fast-MLX-6bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast-MLX-6bit) |
| Noema 1.5 4B Fast | MLX 4-bit | [NoemaAI-labs/Noema-1.5-4B-Fast-MLX-4bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-4B-Fast-MLX-4bit) |
| Noema 1.5 2B | Transformers | [NoemaAI-labs/Noema-1.5-2B](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B) |
| Noema 1.5 2B | GGUF | [NoemaAI-labs/Noema-1.5-2B-GGUF](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B-GGUF) |
| Noema 1.5 2B | MLX BF16 | [NoemaAI-labs/Noema-1.5-2B-MLX-BF16](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B-MLX-BF16) |
| Noema 1.5 2B | MLX 8-bit | [NoemaAI-labs/Noema-1.5-2B-MLX-8bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B-MLX-8bit) |
| Noema 1.5 2B | MLX 6-bit | [NoemaAI-labs/Noema-1.5-2B-MLX-6bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B-MLX-6bit) |
| Noema 1.5 2B | MLX 4-bit | [NoemaAI-labs/Noema-1.5-2B-MLX-4bit](https://huggingface.co/NoemaAI-labs/Noema-1.5-2B-MLX-4bit) |
| Noema 2B | Transformers | [NoemaAI-labs/Noema-2B](https://huggingface.co/NoemaAI-labs/Noema-2B) |
| Noema 2B | GGUF | [NoemaAI-labs/Noema-2B-GGUF](https://huggingface.co/NoemaAI-labs/Noema-2B-GGUF) |

Noema 2B has Transformers and GGUF repositories only. GGUF files are named after the repository and quantization, for example `Noema-1.5-4B-Fast-Q4_K_M.gguf`.

## Lineage

Each model page credits the foundation model it was trained from.

- **Noema 1.5 4B Deep:** Qwen3.5-4B → Noema 1.5 4B Fast → Noema 1.5 4B Deep
- **Noema 1.5 4B Fast:** Qwen3.5-4B → Noema 1.5 4B Fast
- **Noema 1.5 2B:** Qwen3.5-2B → Noema 2B → Noema 1.5 2B
- **Noema 2B:** Qwen3.5-2B → Noema 2B

## Related documentation
- [Run Noema models](https://noemaai.com/docs/run-noema-models)
- [Prompt format and sampling](https://noemaai.com/docs/prompt-format)
- [Model licenses](https://noemaai.com/docs/model-licenses)
- [Evaluation methodology](https://noemaai.com/docs/evaluation-methodology)