What are the hardware requirements for Frontis MA1 35B?

Frontis MA1 35B requires approximately 69.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Frontis MA1 35B and how large is it?

Frontis MA1 35B is developed by FrontisAI, a model with 35b 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 Frontis MA1 35B?

Frontis MA1 35B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Frontis MA1 35B by FrontisAI — VRAM 69.6GB

Name: Frontis MA1 35B
Author: FrontisAI

Frontis MA1 35B is an open-source language model by FrontisAI. Features: 35b LLM, VRAM: 69.6GB, License: cc-by-nc-4.0, LLM Explorer Score: 0.27.

Arxiv:2607.28568 Agent Autoresearch Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-35b-a3... Coding Conversational Endpoints compatible Frontis-ma1 Image-text-to-text Machine-learning-engineering Moe Multimodal Openmle Post-training Qwen3 Qwen3.6 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Vision

Model Card on HF 🤗: https://huggingface.co/FrontisAI/Frontis-MA1-35B

Frontis MA1 35B Parameters and Internals

LLM Name	Frontis MA1 35B
Repository 🤗	https://huggingface.co/FrontisAI/Frontis-MA1-35B
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	69.6 GB
Updated	2026-08-08
Maintainer	FrontisAI
Model Type	qwen3_5_moe
Model Files	5.3 GB: 0-of-15 4.9 GB: 1-of-15 4.9 GB: 2-of-15 4.9 GB: 3-of-15 4.9 GB: 4-of-15 4.9 GB: 5-of-15 4.9 GB: 6-of-15 4.9 GB: 7-of-15 4.9 GB: 8-of-15 4.9 GB: 9-of-15 4.9 GB: 10-of-15 4.9 GB: 11-of-15 4.9 GB: 12-of-15 5.4 GB: 13-of-15 0.1 GB: 14-of-15 2.6 GB
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	cc-by-nc-4.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Frontis MA1 35B 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 Frontis MA1 35B

Best Alternatives	Context / RAM	Downloads	Likes
....5 35B A3B Sceptic V3 1M W4A16	1024K / 26.1 GB	223	0
...AgentWorld 35B A3B Abliterated	256K / 69.2 GB	962	18
Ornith 1.5 35B A3B NPU2	256K / GB	83	1
Qwen3.6 35B A3B NPU2	256K / GB	88	0
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	1418212	506
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665

Note: green Score (e.g. "73.2") means that the model is better than FrontisAI/Frontis-MA1-35B.