What are the hardware requirements for Tev1 0.8B Experimental?

Tev1 0.8B Experimental requires approximately 1.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tev1 0.8B Experimental and how large is it?

Tev1 0.8B Experimental is developed by togethercomputer, a model with 0.8b 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 Tev1 0.8B Experimental?

Tev1 0.8B Experimental is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tev1 0.8B Experimental by togethercomputer — VRAM 1.8GB

Name: Tev1 0.8B Experimental
Author: togethercomputer

Tev1 0.8B Experimental is an open-source language model by togethercomputer. Features: 0.8b LLM, VRAM: 1.8GB, LLM Explorer Score: 0.37.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-0.8b Conversational Decision-model Endpoints compatible Experimental Image-text-to-text Qwen3.5 Qwen3 5 Region:us Safetensors Sharded Tensorflow Together-ai

Model Card on HF 🤗: https://huggingface.co/togethercomputer/Tev1-0.8B-experimental

Tev1 0.8B Experimental Parameters and Internals

LLM Name	Tev1 0.8B Experimental
Repository 🤗	https://huggingface.co/togethercomputer/Tev1-0.8B-experimental
Base Model(s)	Qwen/Qwen3.5-0.8B Qwen/Qwen3.5-0.8B
Model Size	0.8b
Required VRAM	1.8 GB
Updated	2026-09-28
Maintainer	togethercomputer
Model Type	qwen3_5
Model Files	1.8 GB: 1-of-1
Model Architecture	Qwen3_5ForConditionalGeneration
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Tev1 0.8B Experimental 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 Tev1 0.8B Experimental

Best Alternatives	Context / RAM	Downloads	Likes
OvisOCR2	0K / 1.7 GB	197760	473
Qwen3.5 0.8B	0K / 1.8 GB	2839884	655
Intern Decision 0.8B	0K / 0.2 GB	242	16
Qwen3.5 0.8B Base	0K / 1.8 GB	828054	92
PlayJev 0.8B	0K / 2.2 GB	353	2
...iptagent Qwen35 0.8B V2 Merged	0K / 3.4 GB	367	3
Qwen3.5 0.8B	0K / 1.8 GB	47663	19
ORP 0.8B	0K / 1.7 GB	509	1
Qwen3.5 0.8B Manumit V2	0K / 1.7 GB	593	0
Ov Intent Analysis Sft	0K / 3.2 GB	1069	1

Note: green Score (e.g. "73.2") means that the model is better than togethercomputer/Tev1-0.8B-experimental.