What are the hardware requirements for Med Orca Instruct 33B GPTQ?

Med Orca Instruct 33B GPTQ requires approximately 17.6 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Med Orca Instruct 33B GPTQ and how large is it?

Med Orca Instruct 33B GPTQ is developed by yhyhy3, a model with 33b 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 Med Orca Instruct 33B GPTQ?

Med Orca Instruct 33B GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Med Orca Instruct 33B GPTQ by yhyhy3 — VRAM 17.6GB, 2K context

Name: Med Orca Instruct 33B GPTQ
Author: yhyhy3

Med Orca Instruct 33B GPTQ is an open-source language model by yhyhy3. Features: 33b LLM, VRAM: 17.6GB, Context: 2K, Quantized, Instruction-Based, LLM Explorer Score: 0.08.

4bit Autotrain compatible Code Dataset:bigcode/starcoderdata Dataset:c-s-ale/dolly-15k-inst... Dataset:ehartford/dolphin Dataset:linhduong/chatdoctor-2... Dataset:sahil2801/code instruc... Dataset:tiiuae/falcon-refinedw... Dataset:togethercomputer/redpa... En Endpoints compatible Gptq Instruct Llama Medical Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/yhyhy3/med-orca-instruct-33b-GPTQ

Med Orca Instruct 33B GPTQ Parameters and Internals

Model Type

LlamaForCausalLM

Supported Languages

en (proficient)

Training Details

Data Sources:

ehartford/dolphin, LinhDuong/chatdoctor-200k, sahil2801/code_instructions_120k, c-s-ale/dolly-15k-instruction-alpaca-format

Training Time:

23 hours

Hardware Used:

8x A6000 on Community Cloud

LLM Name	Med Orca Instruct 33B GPTQ
Repository 🤗	https://huggingface.co/yhyhy3/med-orca-instruct-33b-GPTQ
Model Size	33b
Required VRAM	17.6 GB
Updated	2025-03-02
Maintainer	yhyhy3
Model Type	llama
Instruction-Based	Yes
Model Files	17.6 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq\|4bit
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.31.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Med Orca Instruct 33B GPTQ 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 Med Orca Instruct 33B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...epseek Coder 33B Instruct GPTQ	16K / 17.4 GB	267	25
Sorceroboros 33B S2a4 Gptq	8K / 17.6 GB	7	3
...er 33B Instruct 4.0bpw H6 EXL2	16K / 17.1 GB	5	5
...er 33B Instruct 8.0bpw H8 EXL2	16K / 33.6 GB	6	3
...er 33B Instruct 3.0bpw H6 EXL2	16K / 13 GB	10	1
...r 33B Instruct 4.65bpw H6 EXL2	16K / 19.8 GB	6	1
...er 33B Instruct 5.0bpw H6 EXL2	16K / 21.2 GB	5	1
...ardLM 33B V1.0 Uncensored GPTQ	2K / 16.9 GB	47	42
Deepseek Wizard 33B Slerp	16K / 35.3 GB	7	0
ValidateAI 3 33B Ties	16K / 66.5 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than yhyhy3/med-orca-instruct-33b-GPTQ.