What are the hardware requirements for Webbrain Compass Tiny Xs V3?

Webbrain Compass Tiny Xs V3 requires approximately 3.4 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Webbrain Compass Tiny Xs V3 and how large is it?

Webbrain Compass Tiny Xs V3 is developed by webbrain-one, a model with 1.7b 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 Xs V3?

Webbrain Compass Tiny Xs V3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Webbrain Compass Tiny Xs V3 by webbrain-one — VRAM 3.4GB, 1024K context

Name: Webbrain Compass Tiny Xs V3
Author: webbrain-one

Webbrain Compass Tiny Xs V3 is an open-source language model by webbrain-one. Features: 1.7b LLM, VRAM: 3.4GB, Context: 1024K, License: other, LLM Explorer Score: 0.3.

Base model:adapter:xhtoken/spa... Base model:xhtoken/spark-x2.5-... Conversational Custom code Lora Region:us Safetensors Sharded Spark2 5 Tensorflow Tool-calling Webbrain

Model Card on HF 🤗: https://huggingface.co/webbrain-one/webbrain-compass-tiny-xs-v3

Webbrain Compass Tiny Xs V3 Parameters and Internals

LLM Name	Webbrain Compass Tiny Xs V3
Repository 🤗	https://huggingface.co/webbrain-one/webbrain-compass-tiny-xs-v3
Base Model(s)	XHToken/Spark-X2.5-1.7B XHToken/Spark-X2.5-1.7B
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-10-09
Maintainer	webbrain-one
Model Type	spark2_5
Model Files	2.0 GB: 1-of-2 1.4 GB: 2-of-2
Model Architecture	Spark2_5ForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.16.1
Tokenizer Class	TokenizersBackend
Padding Token	<｜▁pad▁｜>
Vocabulary Size	131072
LoRA Model	Yes

Rank the Webbrain Compass Tiny Xs V3 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 Xs V3

Best Alternatives	Context / RAM	Downloads	Likes
Hunter 1 1.7B	1024K / 3.4 GB	48	2
Spark X2.5 1.7B	1024K / 3.4 GB	197	42
Spark 1.7B Engram	1024K / 1.6 GB	514	1
Spark X2.5 1.7B Orth R11	1024K / 3.4 GB	370	0
Spark X2.5 1.7B Base	1024K / 3.4 GB	226	5
Spark X2.5 1.7B INT8	1024K / 2 GB	120	9
Spark X2.5 1.7B FP8	1024K / 2 GB	91	8
Feihua N2 1.7B	1024K / 3.4 GB	84	0
...park X2.5 1.7B Ridge 4 6 8 Mlx	1024K / 1.2 GB	14	1
Spark X2.5 1.7B Chat Mlx 4bit	1024K / 1 GB	68	1