Skip to main content
← Back to news

Nanbeige4.3-33B: 33B MoE with 4 GB of RAM, MIT license, multilingual with Italian support

Model releases
Source:Hugging Face
Nanbeige4.3-33B is a 33B MoE with 3B active parameters, built for low-RAM devices: quantized, it fits in roughly 4 GB and runs with Ollama on a laptop, Raspberry Pi or Mac mini, with Ollama Cloud and OpenAI-API-compatible clients also supported. MIT license, multilingual — Italian tops the list of 20+ supported languages.
Read original article

Related articles

Ling 3.1 Flash: 560B open-weight with MIT license and 1M context — what changes if you have 24GB of VRAM

Ling 3.1 Flash ships 560B open-weight parameters under an MIT license with 1M context. It won't fit in 24GB of VRAM, but the quantizations, 25B active MoE and the real numbers change the calculation.

Qwen: the open model with the best multilingual support

Qwen is the open family with the best support for Italian and French: generations, sizes, MoE, when to use it, and a quick comparison with Llama.

MagpieTTS 357M: 12-language speech synthesis that runs on a laptop

NVIDIA's MagpieTTS Multilingual 357M: 12 languages, Italian included, in a 332 MB file that runs locally on a laptop without a GPU. Requirements, a three-command setup, and the honest limits.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🔶

OpenAI API

Inference

Inference API for OpenAI's frontier models (GPT series). You pay per token: a fixed price per million input and output tokens, no GPUs to manage, with rate limits per account tier.

🌏

inclusionAI Ling 3.1 Flash (MoE)

Models

Modello MoE open-weight di inclusionAI: 560B parametri totali, 25B attivi per token, architettura ibrida (attenzione lineare KDA + Gated MLA), finestra di contesto fino a 1M di token, licenza MIT. Reasoning ibrido con modalità di pensiero on/off. A 4 bit entra in 512GB di memoria unificata.

🟠

Anthropic Claude

Inference

Inference API for Anthropic's Claude models (Claude 1 since 2023). Like OpenAI, you pay per token, input and output, with request limits per plan: the frontier path with no servers of your own.

🧭

OpenRouter

Inference

Cloud gateway for LLM inference: a single API endpoint for hundreds of models (including open-weight MoE), with per-token pricing and automatic routing across providers. For Ling 3.1 Flash: $0.075/M input, $0.225/M output.

Browse all resources