Model release

Palmyra-mini

Palmyra-mini is an open-weight model release in the Palmyra family from Writer1 2, version palmyra-mini, released Sep 11, 2025. Its weights can be downloaded by the public1 4 under the Apache License 2.01.

A small text model from Writer, fine-tuned from Qwen2.5-1.5B, that the model card lists at 1.7 billion parameters with a 131,072-token context window. It is the non-reasoning member of the three-model Palmyra-mini family that Writer released in September 2025.1 2

Model hub: Model card (Hugging Face) (external site: huggingface.co)
Model hub: GGUF build (external site: huggingface.co)
Model hub: MLX build (external site: huggingface.co)
Release notes: Palmyra-mini announcement (Hugging Face blog) (external site: huggingface.co)
Release notes: Writer engineering post on Palmyra-mini (external site: writer.com)

On AI on Hugging Face: Qwen/Qwen2.5-1.5B, Writer/palmyra-mini, Writer/palmyra-mini-GGUF, Writer/palmyra-mini-MLX-BF16

Last reviewedSep 29, 2026Entry updated Sep 29, 2026Documented release Sep 11, 2025

Availability and license

Overall availability

Public

Downloadable from Hugging Face without gating.1

Availability fact review: not separately recorded

Availability is separate from permission: read the license before using or redistributing.

Apache License 2.0 (external site: huggingface.co)1
Applies to: Weights · SPDX Apache-2.0 · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the Apache License 2.0

The card's license field is Apache 2.0. The base model, Qwen2.5-1.5B, is also listed under Apache 2.0 on its own model card.1 7

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.

weights: Unknown — no complete fact-level rights review
code: Unknown — no complete fact-level rights review
data: Unknown — no complete fact-level rights review
documentation: Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.2. An editorial category, not a certification.

Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.

Public materials checklist for Palmyra-mini
Item	Status	Notes and evidence
WeightsCan the general public download the model parameters for this release?	Public	Writer also publishes GGUF and MLX conversions.1 4
Inference codeIs code for running the model published?	Public	The card documents inference with Hugging Face Transformers and serving with vLLM.1
Training codeIs the code used to train the model published?	Unknown	Not assessed.
Training-data informationDoes the information cover provenance, scope, acquisition, selection, labeling, processing, and where data or alternatives can be obtained? Access alone does not establish completeness.	Unknown	Not assessed.
Training-data accessCan the training data be obtained? This is independent of information completeness and reuse rights; original unshareable data need not be downloadable.	Unknown	Not assessed.
Complete training pipelineIs the complete base-training and preprocessing pipeline published, including configuration? Fine-tuning code or an inference SDK alone is insufficient.	Unknown	Not assessed.
Legacy data assessment (v0.1)Historical assessment combining download access and disclosure. Preserved for traceability; excluded from the v0.2 tier calculation. See the new separate assessments above.	Unknown	Neither the model card nor Writer's announcements name the fine-tuning data.1 2
Training recipeAre the training configuration and procedure documented in enough detail to follow?	Unknown	Not assessed.
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.	Partial	The card publishes benchmark scores without evaluation code or configurations.1

What it is useful for

The model card describes it as intended for research and development in generative AI, particularly tasks that need mathematical and logical reasoning. Writer's engineering post describes running the Palmyra-mini models locally, including on an iPhone with llama.cpp.1 3

Organization context

Writer

Provenance and derivatives

Fine-tuned by Writer from Qwen2.5-1.5B, a base model in Alibaba Cloud's Qwen family.1 7 8

Derived from: Qwen2.5-1.5B (external site: huggingface.co) — Base model (Apache 2.0 per its card).

Other releases in the Palmyra family

Palmyra-mini-thinking-bModel-disclosure tier (USASI rubric v0.2): Open-weight

Palmyra family overview

What this catalog does not know

Unknown means the sources reviewed for this record do not document it. It is not evidence that something does not exist.

Training code: unknown.
Training-data information: unknown.
Training-data access: unknown.
Complete training pipeline: unknown.
Legacy data assessment (v0.1): unknown.
Training recipe: unknown.

Have a primary source? How to report a correction.

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

Published by Writer, Inc., which is headquartered in San Francisco per its company page and platform services agreement. The base model, Qwen2.5-1.5B, comes from Alibaba Cloud's Qwen family and is not thereby U.S.-developed; eligibility here rests on Writer as the developer and maintainer of this fine-tune.1 5 6 8

Assessed Sep 29, 2026

Sources

1.
Writer/palmyra-mini model card (external site: huggingface.co)
Writer · Model card · accessed Sep 29, 2026
2.
Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason! (external site: huggingface.co)
Writer · Announcement · published Sep 11, 2025 · accessed Sep 29, 2026
3.
Writer releases a trio of small, powerful 1.5B parameter models to the open source community (external site: writer.com)
Writer · Announcement · published Sep 19, 2025 · accessed Sep 29, 2026
4.
Writer on Hugging Face (external site: huggingface.co)
Writer · Repository · accessed Sep 29, 2026
5.
Company | WRITER (external site: writer.com)
Writer · Official page · accessed Sep 29, 2026
6.
Writer platform services agreement (external site: writer.com)
Writer, Inc. · Official page · published Aug 5, 2026 · accessed Sep 29, 2026
7.
Qwen/Qwen2.5-1.5B model card (external site: huggingface.co)
Qwen (Alibaba Cloud) · Model card · accessed Sep 29, 2026
8.
Qwen on Hugging Face (external site: huggingface.co)
Qwen (Alibaba Cloud) · Repository · accessed Sep 29, 2026

Email a correction Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.

Cite this page

APA style

USASI. (2026, September 29). Palmyra-mini. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/open/palmyra-mini/

BibTeX

@misc{usasi_palmyra_mini,
  author = {{USASI}},
  title = {Palmyra-mini},
  year = {2026},
  month = sep,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/open/palmyra-mini/}},
  note = {United States of America Superintelligence. Last updated 2026-09-29}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

For maintainers: a “Listed in USASI” badge

Links to this page. It says the entry is listed, not endorsed or rated. About the badge

Markdown (for a README)

[![Listed in the USASI catalog](https://unitedstatesofamericasuperintelligence.com/badges/listed.svg)](https://unitedstatesofamericasuperintelligence.com/open/palmyra-mini/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/open/palmyra-mini/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/listed.svg" alt="Listed in the USASI catalog" height="20"></a>