What are the hardware requirements for Axion 1.0 35B?

Axion 1.0 35B requires approximately 5.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Axion 1.0 35B and how large is it?

Axion 1.0 35B is developed by Axion1-0, 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 Axion 1.0 35B?

Axion 1.0 35B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Axion 1.0 35B by Axion1-0 — VRAM 5.4GB

Name: Axion 1.0 35B
Author: Axion1-0

Axion 1.0 35B is an open-source language model by Axion1-0. Features: 35b LLM, VRAM: 5.4GB, License: apache-2.0.

Arxiv:2611.03233 Agent Conversational Dataset:axion1-0/axion-trainin... Endpoints compatible Image-text-to-text Moe Qwen3 5 moe Region:us Reproduction Safetensors Scientific-reasoning Tool-use

Model Card on HF 🤗: https://huggingface.co/Axion1-0/Axion-1.0-35B

Axion 1.0 35B Parameters and Internals

LLM Name	Axion 1.0 35B
Repository 🤗	https://huggingface.co/Axion1-0/Axion-1.0-35B
Model Size	35b
Required VRAM	5.4 GB
Updated	2026-11-05
Maintainer	Axion1-0
Model Type	qwen3_5_moe
Model Files	6.0 GB 5.6 GB 6.1 GB 5.6 GB 6.1 GB 5.6 GB 6.3 GB 5.5 GB 6.1 GB 5.6 GB 6.3 GB 5.4 GB
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.5.4
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Axion 1.0 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 Axion 1.0 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	58	0
Qwen3.6 35B A3B NPU2	256K / GB	82	0
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
JEV 35B	0K / 72.3 GB	713162	403
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	1458200	519
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343

Note: green Score (e.g. "73.2") means that the model is better than Axion1-0/Axion-1.0-35B.