What are the hardware requirements for T1 122B A10B?

T1 122B A10B requires approximately 206.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed T1 122B A10B and how large is it?

T1 122B A10B is developed by TberiusJunyao, a model with 122b 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 T1 122B A10B?

T1 122B A10B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

T1 122B A10B by TberiusJunyao — VRAM 206.4GB

Name: T1 122B A10B
Author: TberiusJunyao

T1 122B A10B is an open-source language model by TberiusJunyao. Features: 122b LLM, VRAM: 206.4GB, License: cc-by-4.0, LLM Explorer Score: 0.29.

Arxiv:2609.11042 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-122b-a... Conversational Endpoints compatible Image-text-to-text Qwen3 5 Qwen3 5 moe Recursive-task-synthesis Region:us Safetensors Sharded Supervised-fine-tuning Tensorflow Terminal-agents

Model Card on HF 🤗: https://huggingface.co/TberiusJunyao/T1-122B-A10B

T1 122B A10B Parameters and Internals

LLM Name	T1 122B A10B
Repository 🤗	https://huggingface.co/TberiusJunyao/T1-122B-A10B
Base Model(s)	Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B
Model Size	122b
Required VRAM	206.4 GB
Updated	2026-09-13
Maintainer	TberiusJunyao
Model Type	qwen3_5_moe
Model Files	4.8 GB: 1-of-52 4.8 GB: 2-of-52 4.8 GB: 3-of-52 4.8 GB: 4-of-52 4.8 GB: 5-of-52 4.8 GB: 6-of-52 4.8 GB: 7-of-52 4.8 GB: 8-of-52 4.8 GB: 9-of-52 4.8 GB: 10-of-52 4.8 GB: 11-of-52 4.8 GB: 12-of-52 4.8 GB: 13-of-52 4.8 GB: 14-of-52 4.8 GB: 15-of-52 4.8 GB: 16-of-52 4.8 GB: 17-of-52 4.8 GB: 18-of-52 4.8 GB: 19-of-52 4.8 GB: 20-of-52 4.8 GB: 21-of-52 4.8 GB: 22-of-52 4.8 GB: 23-of-52 4.8 GB: 24-of-52 4.8 GB: 25-of-52 4.8 GB: 26-of-52 4.8 GB: 27-of-52 4.8 GB: 28-of-52 4.8 GB: 29-of-52 4.8 GB: 30-of-52 4.8 GB: 31-of-52 4.8 GB: 32-of-52 4.8 GB: 33-of-52 4.8 GB: 34-of-52 4.8 GB: 35-of-52 4.8 GB: 36-of-52 4.8 GB: 37-of-52 4.8 GB: 38-of-52 4.8 GB: 39-of-52 4.8 GB: 40-of-52 4.8 GB: 41-of-52 4.8 GB: 42-of-52 4.8 GB: 43-of-52
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	cc-by-4.0
Transformers Version	4.57.0.dev0

Rank the T1 122B A10B 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 T1 122B A10B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 122B A10B NVFP4	0K / 83.5 GB	248732	49
Qwen3.5 122B A10B	0K / 248.6 GB	2139628	605
Qwen3.5 122B A10B	0K / 248.6 GB	45	1
Qwen3.5 122B A10B	0K / 248.6 GB	1680	8
Qwen3.5 122B A10B Abliterated	0K / 248.6 GB	59	5
Qwen3.5 122B A10B FP8	0K / 126.3 GB	1271983	112
Qwen3.5 122B A10B NVFP4	0K / 74 GB	18267	18
...en3.5 122B A10B Int4 AutoRound	0K / 72 GB	142311	45
AREX Base	0K / 164.2 GB	389	21
Qwen3.5 122B A10B WMix48	0K / 73.2 GB	215	3

Note: green Score (e.g. "73.2") means that the model is better than TberiusJunyao/T1-122B-A10B.