What are the hardware requirements for Webbrain Compass Tiny V2?

Webbrain Compass Tiny V2 requires approximately 5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Webbrain Compass Tiny V2 and how large is it?

Webbrain Compass Tiny V2 is developed by webbrain-one, a model with 2b 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 Webbrain Compass Tiny V2?

Webbrain Compass Tiny V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Webbrain Compass Tiny V2 by webbrain-one — VRAM 5GB, 128K context

Name: Webbrain Compass Tiny V2
Author: webbrain-one

Webbrain Compass Tiny V2 is an open-source language model by webbrain-one. Features: 2b LLM, VRAM: 5GB, Context: 128K, License: other.

Base model:finetune:openbmb/mi... Base model:openbmb/minicpm5-2b Bf16 Conversational Endpoints compatible Experimental Llama Lora Lora-merged Region:us Safetensors Sharded Tensorflow Tool-calling Web-agent

Model Card on HF 🤗: https://huggingface.co/webbrain-one/webbrain-compass-tiny-v2

Webbrain Compass Tiny V2 Parameters and Internals

LLM Name	Webbrain Compass Tiny V2
Repository 🤗	https://huggingface.co/webbrain-one/webbrain-compass-tiny-v2
Base Model(s)	MiniCPM5 2B openbmb/MiniCPM5-2B
Model Size	2b
Required VRAM	5 GB
Updated	2026-09-14
Maintainer	webbrain-one
Model Type	llama
Model Files	4.0 GB: 1-of-2 1.0 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	5.16.1
Tokenizer Class	TokenizersBackend
Padding Token	</s>
Vocabulary Size	130560
LoRA Model	Yes

Rank the Webbrain Compass Tiny V2 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 Webbrain Compass Tiny V2

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM5 2B Base	512K / 5 GB	54	17
MiniCPM5 2B	128K / 5 GB	2879	623
MiniCPM5 2B MLX	128K / 1.4 GB	288	24
...iniCPM5 2B SFT Pashto Instruct	128K / 5 GB	1076	0
...iniCPM5 2B Heretic Abliterated	128K / 5 GB	510	1
MiniCPM5 2B Heretic	128K / 5 GB	610	0
MiniCPM5 2B Mlx Mxfp4	128K / 1.3 GB	206	1
MiniCPM5 2B Catalan Chat	128K / 5 GB	285	0
MiniCPM5 2B Midtrain	128K / 5 GB	51	17
MiniCPM5 2B SFT	128K / 5 GB	47	22

Note: green Score (e.g. "73.2") means that the model is better than webbrain-one/webbrain-compass-tiny-v2.