What are the hardware requirements for InstructPalmyra 20B?

InstructPalmyra 20B requires approximately 40.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InstructPalmyra 20B and how large is it?

InstructPalmyra 20B is developed by Writer, a model with 20b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does InstructPalmyra 20B perform on standard benchmarks?

InstructPalmyra 20B has the following published scores: MMLU 28.26. Compare against reference models on this page or on the LLM Explorer leaderboards.

InstructPalmyra 20B by Writer — VRAM 40.6GB

Name: InstructPalmyra 20B
Author: Writer

InstructPalmyra 20B is an open-source language model by Writer. Features: 20b LLM, VRAM: 40.6GB, License: apache-2.0, LLM Explorer Score: 0.1, Arc: 47.1, HellaSwag: 73, MMLU: 28.3, GSM8K: 2.6.

Dataset:writer/palmyra-data-in... En Endpoints compatible Gpt2 Hf Instructgpt Palmyra Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/Writer/InstructPalmyra-20b

InstructPalmyra 20B Parameters and Internals

Model Type

Causal decoder-only

Use Cases

Areas:

Research, Commercial applications

Applications:

Virtual assistants, Customer support, Content generation

Primary Use Cases:

Advanced natural language processing and comprehension

Limitations:

Primarily trained on English data; may not generalize to other languages, Potential offensive content and biases

Considerations:

Develop guardrails and take appropriate precautions for any production use.

Additional Notes

Developed to address the growing demand for advanced natural language processing.

Supported Languages

en (proficient)

Training Details

Data Sources:

Writer/palmyra-data-index

Data Volume:

approximately 70,000 instruction-response records

Model Architecture:

Transformer Decoder

Responsible Ai Considerations

Fairness:

Difficult to predict responses; may contain biases and offensive content.

Mitigation Strategies:

Recommended to curate or filter outputs before release.

LLM Name	InstructPalmyra 20B
Repository 🤗	https://huggingface.co/Writer/InstructPalmyra-20b
Model Size	20b
Required VRAM	40.6 GB
Updated	2026-08-08
Maintainer	Writer
Model Type	gpt2
Model Files	9.9 GB: 1-of-5 10.0 GB: 2-of-5 10.0 GB: 3-of-5 10.0 GB: 4-of-5 0.7 GB: 5-of-5
Supported Languages	en
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Model Max Length	2048
Transformers Version	4.32.0.dev0
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50258
Torch Data Type	float16
Activation Function	gelu
Errors	replace

Rank the InstructPalmyra 20B 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 InstructPalmyra 20B

Best Alternatives	Context / RAM	Downloads	Likes
Palmyra 20B Chat	0K / 40.6 GB	173	11
Palmyra Med 20B	0K / 40.6 GB	224	37
GPT Sw3 20B Instruct	0K / 83.2 GB	1129	12
GPT Sw3 20B	0K / 83.2 GB	1512	2

Note: green Score (e.g. "73.2") means that the model is better than Writer/InstructPalmyra-20b.