What are the hardware requirements for Edge0 35B A3B Preview?

Edge0 35B A3B Preview requires approximately 19.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Edge0 35B A3B Preview and how large is it?

Edge0 35B A3B Preview is developed by Edge0, a model with 34.7b 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 Edge0 35B A3B Preview?

Edge0 35B A3B Preview is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Edge0 35B A3B Preview by Edge0 — VRAM 19.6GB

Name: Edge0 35B A3B Preview
Author: Edge0

Edge0 35B A3B Preview is an open-source language model by Edge0. Features: 34.7b LLM, VRAM: 19.6GB, License: apache-2.0, MoE, LLM Explorer Score: 0.44.

4-bit Conversational Edge-inference Lora Mlx Moe Prerouter Qwen3 5 moe Region:us Safetensors Sharded Ssd-offload Tensorflow

Model Card on HF 🤗: https://huggingface.co/Edge0/Edge0-35B-A3B-preview

Edge0 35B A3B Preview Parameters and Internals

LLM Name	Edge0 35B A3B Preview
Repository 🤗	https://huggingface.co/Edge0/Edge0-35B-A3B-preview
Base Model(s)	Qwen/Qwen3.5-MoE-35B-A3B Qwen/Qwen3.5-MoE-35B-A3B
Model Size	34.7b
Required VRAM	19.6 GB
Updated	2026-09-11
Maintainer	Edge0
Model Type	qwen3_5_moe
Model Files	0.0 GB 4.4 GB: 1-of-4 5.4 GB: 2-of-4 5.4 GB: 3-of-4 4.4 GB: 4-of-4 0.1 GB
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
LoRA Model	Yes
Errors	replace

Rank the Edge0 35B A3B Preview 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 Edge0 35B A3B Preview

Best Alternatives	Context / RAM	Downloads	Likes
Affine 5dfqbbh8ev Sft	0K / 69.3 GB	388	0
5eqdtdzqle Ckpt1000 M7	0K / 71.7 GB	22	0
Agents A1 OptiQ 4bit	0K / 22.2 GB	891	3
...CybersecurityLLM V1.0 Mlx 4Bit	0K / 19.5 GB	689	46
KAT Coder V2.5 Dev OptiQ 4bit	0K / 21.9 GB	114	3
XYZ Aquila Mini OptiQ 4bit	0K / 36.3 GB	34	3