What are the hardware requirements for Math Instruct V1?

Math Instruct V1 requires approximately 1.2 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 Math Instruct V1 and how large is it?

Math Instruct V1 is developed by kaushik-harsh-99, a model with 0.6b 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 Math Instruct V1?

Math Instruct V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Math Instruct V1 by kaushik-harsh-99 — VRAM 1.2GB, 32K context

Name: Math Instruct V1
Author: kaushik-harsh-99

Math Instruct V1 is an open-source language model by kaushik-harsh-99. Features: 0.6b LLM, VRAM: 1.2GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-0.6b Dataset:nvidia/openmathinstruc... En Endpoints compatible Instruct Math Mathematics Qwen3 Region:us Safetensors Sft

Model Card on HF 🤗: https://huggingface.co/kaushik-harsh-99/Math-Instruct-v1

Math Instruct V1 Parameters and Internals

LLM Name	Math Instruct V1
Repository 🤗	https://huggingface.co/kaushik-harsh-99/Math-Instruct-v1
Base Model(s)	Qwen/Qwen3-0.6B Qwen/Qwen3-0.6B
Model Size	0.6b
Required VRAM	1.2 GB
Updated	2026-08-05
Maintainer	kaushik-harsh-99
Model Type	qwen3
Instruction-Based	Yes
Model Files	1.2 GB
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Math Instruct V1 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 Math Instruct V1

Best Alternatives	Context / RAM	Downloads	Likes
Quipu 0.6B	40K / 1.2 GB	351	4
Supertron2.1 0.6B	40K / 0.8 GB	0	2
Qwen3 0.6B Instruct	40K / 1.5 GB	29	0
Luth 0.6B Instruct	40K / 1.2 GB	324	9
... 0.6B Instruction Finetuned V2	32K / 1.2 GB	17	0
...en3 0.6B Instruction Finetuned	32K / 1.2 GB	49	0

Note: green Score (e.g. "73.2") means that the model is better than kaushik-harsh-99/Math-Instruct-v1.