What are the hardware requirements for Mercury Acad 1.7B?

Mercury Acad 1.7B requires approximately 3.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mercury Acad 1.7B and how large is it?

Mercury Acad 1.7B is developed by rrchat, 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 Mercury Acad 1.7B?

Mercury Acad 1.7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mercury Acad 1.7B by rrchat — VRAM 3.8GB

Name: Mercury Acad 1.7B
Author: rrchat

Mercury Acad 1.7B is an open-source language model by rrchat. Features: 2b LLM, VRAM: 3.8GB, License: apache-2.0, LLM Explorer Score: 0.29.

Agent Base model:finetune:liquidai/l... Base model:liquidai/lfm3-vl-2b Code Conversational Custom code Dataset:huggingfacetb/smoltalk... Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-sft-ag... Dataset:open-r1/openr1-math-22... Dataset:vikhrmodels/grandmaste... En Function-calling Image-text-to-text Lfm Lfm3 Lfm3 vl Liquid-ai Math Mobile Multimodal Reasoning Region:us Ru Russian Safetensors Stem Tool-use Vision

Model Card on HF 🤗: https://huggingface.co/rrchat/Mercury-Acad-1.7B

Mercury Acad 1.7B Parameters and Internals

LLM Name	Mercury Acad 1.7B
Repository 🤗	https://huggingface.co/rrchat/Mercury-Acad-1.7B
Base Model(s)	LFM3 VL 2B LiquidAI/LFM3-VL-2B
Model Size	2b
Required VRAM	3.8 GB
Updated	2026-11-01
Maintainer	rrchat
Model Type	lfm3_vl
Model Files	3.8 GB
Supported Languages	ru en
Model Architecture	Lfm3VlForConditionalGeneration
License	apache-2.0
Transformers Version	5.22.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>

Rank the Mercury Acad 1.7B 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 Mercury Acad 1.7B

Best Alternatives	Context / RAM	Downloads	Likes
LFM3 VL 2B	0K / 3.8 GB	8091	188
Lfm3 Vld 2B Multipass	0K / 3.8 GB	70	16
Lfm3 Vld 2B	0K / 4.4 GB	75	15
LFM3 VL 2B ONNX	0K / GB	283	11
LFM3 VL 2B MLX Bf16	0K / 3.8 GB	968	9
LFM3 VL 2B FP8	0K / 2.6 GB	360	10
LFM3 VL 2B NVFP4	0K / 2.2 GB	213	12
Lfm3 Vl 2B Heretic	0K / 3.8 GB	38	1
Mercury 1.7B	0K / 3.8 GB	30	2
Lfm3 Vld 2B Onnx	0K / GB	38	1

Note: green Score (e.g. "73.2") means that the model is better than rrchat/Mercury-Acad-1.7B.