LLM EXPLORER 62,233 MODELS INDEXED

Tev1 4B Experimental by togethercomputer

By togethercomputer · 1539 downloads
HF Repo ↗ Copy URL

Tev1 4B Experimental is an open-source language model by togethercomputer. Features: 4b LLM, VRAM: 9.3GB, LLM Explorer Score: 0.4.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-4b   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/Tev1-4B-experimental 

Tev1 4B Experimental Parameters and Internals

LLM NameTev1 4B Experimental
Repository 🤗https://huggingface.co/togethercomputer/Tev1-4B-experimental 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM9.3 GB
Updated2026-09-26
Maintainertogethercomputer
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   4.0 GB: 2-of-2
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Tev1 4B Experimental

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 4B0K / 9.3 GB6575502801
NuExtract30K / 0.2 GB441570324
Agents A1 4B0K / 9.1 GB17757872
APUS OpenJev V1 4B0K / 9.1 GB6654
Qwen3.5 4B Base0K / 9.3 GB22781479
CogEvol 4B0K / 9.1 GB86027
Fara1.5 4B0K / 9.1 GB493439
Qwen3.8 4B Distill0K / 9.3 GB187826
Qwen3.5 4B0K / 9.3 GB13996126
Qweble Sol 4B MLX0K / 8.5 GB5351
Note: green Score (e.g. "73.2") means that the model is better than togethercomputer/Tev1-4B-experimental.