Skip to main content
← Back to news

autotrust/JEV-35B: 35B (3B active) decision model in NVFP4

Model releases
Source:Hugging Face
Autotrust releases JEV-35B, a 35B-Parameter (3B active) MoE Decision model fine-tuned on Qwen3.5-35B-A3B for text classification and risk scoring. In NVFP4 Quantization it occupies about 25.6GB of VRAM: it runs on a 32GB GPU without going through the frontier.
Read original article

Related articles

Decision models in local: JEV-35B and the 3B-active System 1

You don't need a big LLM to decide. JEV-35B (35B, 3B active) in NVFP4 on a 32GB GPU and ej (11.4MB) on CPU show how to do routing, classification and quality control without generating a single token.

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.

Llama 3 and Llama 4: Meta's open family — which model runs on your hardware

From the 3.1 8B to the 4 Scout MoE with a 10M context: the Llama family in a table, what runs on 16, 48 and 128 GB of RAM, the Community license translated for the Italian business and the choice by budget.

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.

📊

autotrust/JEV-35B

Models

An open decision model from Autotrust, 35B parameters (3B active), a fine-tune of Qwen3.5-35B-A3B for text classification and risk scoring. In NVFP4 quantization it occupies about 25.6 GB of VRAM: it runs on a 32 GB GPU with no frontier inference needed.

MiniCPM-V 4.7 35B-A3B (MoE)

Models

The first open-source MoE of OpenBMB's MiniCPM-V series: 35.2B total parameters, ~3B active per token, multi-image and video understanding with early visual-token compression (LLaVA-UHD v4). First open-source MoE with fluid on-device decoding — 13+ tok/s on 3GB of RAM on an iPhone 17 Pro Max — thanks to Lookahead Expert Scheduling (llama.cpp-omni), fine per-level quantization and DSpark speculative sampling. Day-0 support for Rockchip, Houmo, Intel, AMD and Arm; runs on Ollama, llama.cpp, vLLM and SGLang.

🧠

Qwen3 30B-A3B (MoE)

Models

Mixture-of-Experts model: 30B total params but only 3.3B active per token. Small-model speed with mid-size quality; the best speed/quality ratio in its class.

🧩

Qwen3.5-35B-A3B

Models

A 35B-parameter MoE model with ~3B active per token from the Qwen family, Apache-2.0. It is the fine-tune base of JEV-35B. Suited to 40GB+ GPUs in BF16 or to 4/8-bit quantizations for smaller hardware.

Browse all resources