What are the hardware requirements for Minotaur 15B 8bit?

Minotaur 15B 8bit requires approximately 16.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Minotaur 15B 8bit and how large is it?

Minotaur 15B 8bit is developed by rahuldshetty, a model with 15b 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 Minotaur 15B 8bit?

Minotaur 15B 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Minotaur 15B 8bit by rahuldshetty — VRAM 16.5GB

Name: Minotaur 15B 8bit
Author: rahuldshetty

Minotaur 15B 8bit is an open-source language model by rahuldshetty. Features: 15b LLM, VRAM: 16.5GB, Quantized, Code Generating, LLM Explorer Score: 0.07.

8-bit 8bit Codegen Endpoints compatible Gpt bigcode Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/rahuldshetty/minotaur-15b-8bit

Minotaur 15B 8bit Parameters and Internals

LLM Name	Minotaur 15B 8bit
Repository 🤗	https://huggingface.co/rahuldshetty/minotaur-15b-8bit
Model Size	15b
Required VRAM	16.5 GB
Updated	2026-07-15
Maintainer	rahuldshetty
Model Type	gpt_bigcode
Model Files	9.9 GB: 1-of-2 6.6 GB: 2-of-2
Quantization Type	8bit
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
Transformers Version	4.30.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	bfloat16
Activation Function	gelu

Rank the Minotaur 15B 8bit 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 Minotaur 15B 8bit

Best Alternatives	Context / RAM	Downloads	Likes
WizardCoder 15B V1.0 8bit	0K / 16.5 GB	3	1
Starcoder 15b 8bit	0K / GB	17	4
Starcoder 15b 8bit	0K / GB	11	4
Starcoder 15b 4bit	0K / GB	12	2
Starcoder 15b 4bit	0K / GB	10	2
...ardCoder Guanaco 15B V1.1 GPTQ	0K / 9.2 GB	50	12
WizardCoder Guanaco 15B V1.1	0K / 31 GB	52	12
...ardCoder Guanaco 15B V1.0 GPTQ	0K / 9.2 GB	57	16
WizardCoder Guanaco 15B V1.0	0K / 31 GB	55	5
MoTCoder 15B V1.0	0K / 30.9 GB	26	2

Note: green Score (e.g. "73.2") means that the model is better than rahuldshetty/minotaur-15b-8bit.