What are the hardware requirements for Index Translate 35B A3B Preview?

Index Translate 35B A3B Preview requires approximately 71.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Index Translate 35B A3B Preview is developed by IndexTeam, 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 Index Translate 35B A3B Preview?

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

Index Translate 35B A3B Preview by IndexTeam — VRAM 71.7GB

Name: Index Translate 35B A3B Preview
Author: IndexTeam

Index Translate 35B A3B Preview is an open-source language model by IndexTeam. Features: 35b LLM, VRAM: 71.7GB, License: apache-2.0, LLM Explorer Score: 0.31.

Arxiv:2609.40181 Index Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Translation

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

Index Translate 35B A3B Preview Parameters and Internals

LLM Name	Index Translate 35B A3B Preview
Repository 🤗	https://huggingface.co/IndexTeam/Index-Translate-35B-A3B-preview
Model Size	35b
Required VRAM	71.7 GB
Updated	2026-10-10
Maintainer	IndexTeam
Model Type	qwen3_5_moe
Model Files	4.3 GB: 1-of-15 5.0 GB: 2-of-15 5.0 GB: 3-of-15 5.1 GB: 4-of-15 5.0 GB: 5-of-15 5.0 GB: 6-of-15 5.1 GB: 7-of-15 5.0 GB: 8-of-15 5.0 GB: 9-of-15 5.1 GB: 10-of-15 5.0 GB: 11-of-15 5.0 GB: 12-of-15 5.0 GB: 13-of-15 5.4 GB: 14-of-15 1.7 GB: 15-of-15
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Index Translate 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 Index Translate 35B A3B Preview

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	76	1
Qwen3.6 35B A3B NPU2	256K / GB	84	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 IndexTeam/Index-Translate-35B-A3B-preview.