What are the hardware requirements for Qwopus MoE 35B A3B?

Qwopus MoE 35B A3B requires approximately 72.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwopus MoE 35B A3B and how large is it?

Qwopus MoE 35B A3B is developed by samuelcardillo, a model with 36b 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 Qwopus MoE 35B A3B?

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

Qwopus MoE 35B A3B by samuelcardillo — VRAM 72.3GB

Name: Qwopus MoE 35B A3B
Author: samuelcardillo

Qwopus MoE 35B A3B is an open-source language model by samuelcardillo. Features: 36b LLM, VRAM: 72.3GB, License: apache-2.0, MoE, LLM Explorer Score: 0.23.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-35b-a3... Claude-opus Dataset:jackrong/qwen3.5-reaso... Dataset:nohurry/opus-4.6-reaso... Dataset:roman1111111/claude-op... Distillation En Moe Qlora Qwen3.5 Qwen3 5 moe Reasoning Region:us Safetensors Sharded Tensorflow Unsloth Zh

Model Card on HF 🤗: https://huggingface.co/samuelcardillo/Qwopus-MoE-35B-A3B

Qwopus MoE 35B A3B Parameters and Internals

LLM Name	Qwopus MoE 35B A3B
Repository 🤗	https://huggingface.co/samuelcardillo/Qwopus-MoE-35B-A3B
Model Name	unsloth/Qwen3.5-35B-A3B
Base Model(s)	Qwen/Qwen3.5-35B-A3B Qwen/Qwen3.5-35B-A3B
Model Size	36b
Required VRAM	72.3 GB
Updated	2026-06-14
Maintainer	samuelcardillo
Model Type	qwen3_5_moe
Model Files	5.4 GB: 1-of-14 5.4 GB: 2-of-14 5.4 GB: 3-of-14 5.4 GB: 4-of-14 5.4 GB: 5-of-14 5.4 GB: 6-of-14 5.4 GB: 7-of-14 5.4 GB: 8-of-14 5.3 GB: 9-of-14 5.4 GB: 10-of-14 5.4 GB: 11-of-14 5.4 GB: 12-of-14 5.4 GB: 13-of-14 2.2 GB: 14-of-14
Supported Languages	en zh
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<\|vision_pad\|>
Torch Data Type	bfloat16
Errors	replace

Rank the Qwopus MoE 35B A3B 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 Qwopus MoE 35B A3B

Best Alternatives	Context / RAM	Downloads	Likes
Affine 5eqdtdzqle Ckpt300 M4	0K / 142.6 GB	548	0
Darwin 35B A3B Opus	0K / 72.3 GB	194	97
Yaya 3.6	0K / 72.2 GB	38	0
Carnice Qwen3.6 MoE 35B A3B	0K / 72.2 GB	0	23

Note: green Score (e.g. "73.2") means that the model is better than samuelcardillo/Qwopus-MoE-35B-A3B.