What are the hardware requirements for Smartyplats 7B V2?

Smartyplats 7B V2 requires approximately 1.1 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smartyplats 7B V2 and how large is it?

Smartyplats 7B V2 is developed by vihangd, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Smartyplats 7B V2 perform on standard benchmarks?

Smartyplats 7B V2 has the following published scores: MMLU 58.16. Compare against reference models on this page or on the LLM Explorer leaderboards.

Smartyplats 7B V2 by vihangd — VRAM 1.1GB, 32K context

Name: Smartyplats 7B V2
Author: vihangd

Smartyplats 7B V2 is an open-source language model by vihangd. Features: 7b LLM, VRAM: 1.1GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 57.9, HellaSwag: 80.8, MMLU: 58.2, GSM8K: 38.8.

Endpoints compatible Mistral Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/vihangd/smartyplats-7b-v2

Smartyplats 7B V2 Parameters and Internals

Model Type

text generation

Training Details

Data Sources:

alpca style datasets

Methodology:

fine-tuning with QLoRA

Input Output

Input Format:

alpaca style prompt template

LLM Name	Smartyplats 7B V2
Repository 🤗	https://huggingface.co/vihangd/smartyplats-7b-v2
Model Size	7b
Required VRAM	1.1 GB
Updated	2026-07-24
Maintainer	vihangd
Model Type	mistral
Model Files	0.3 GB: 1-of-42 0.4 GB: 2-of-42 0.4 GB: 3-of-42 0.3 GB: 4-of-42 0.3 GB: 5-of-42 0.3 GB: 6-of-42 0.4 GB: 7-of-42 0.4 GB: 8-of-42 0.3 GB: 9-of-42 0.3 GB: 10-of-42 0.3 GB: 11-of-42 0.4 GB: 12-of-42 0.4 GB: 13-of-42 0.3 GB: 14-of-42 0.3 GB: 15-of-42 0.3 GB: 16-of-42 0.4 GB: 17-of-42 0.4 GB: 18-of-42 0.3 GB: 19-of-42 0.3 GB: 20-of-42 0.3 GB: 21-of-42 0.4 GB: 22-of-42 0.4 GB: 23-of-42 0.3 GB: 24-of-42 0.3 GB: 25-of-42 0.3 GB: 26-of-42 0.4 GB: 27-of-42 0.4 GB: 28-of-42 0.3 GB: 29-of-42 0.3 GB: 30-of-42 0.3 GB: 31-of-42 0.4 GB: 32-of-42 0.4 GB: 33-of-42 0.3 GB: 34-of-42 0.3 GB: 35-of-42 0.3 GB: 36-of-42 0.4 GB: 37-of-42 0.4 GB: 38-of-42 0.3 GB: 39-of-42 0.3 GB: 40-of-42 0.2 GB: 41-of-42 0.3 GB: 42-of-42 0.3 GB: 1-of-42 0.4 GB: 2-of-42 0.4 GB: 3-of-42
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Smartyplats 7B 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

Quantized Models of the Smartyplats 7B V2

Model	Likes	Downloads	VRAM
Smartyplats 7B V2 GGUF	2	59	3 GB
Smartyplats 7B V2 GPTQ	1	7	4 GB
Smartyplats 7B V2 AWQ	1	7	4 GB

Best Alternatives to Smartyplats 7B V2

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8470	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8018	17
Hebrew Mistral 7B 200K	256K / 30 GB	23	15
Astral 256K 7B	250K / 14.4 GB	9	0
Astral 256K 7B V2	250K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than vihangd/smartyplats-7b-v2.