Palmyra-mini
Release in the Palmyra family · version palmyra-mini
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 2025.12
- 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)
Availability and license
Model-disclosure tier
The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| WeightsCan the general public download the model parameters for this release? | Public | Writer also publishes GGUF and MLX conversions.14 |
| 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 informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access. | Unknown | Neither the model card nor Writer's announcements name the fine-tuning data.12 |
| 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
Organization context
Provenance and derivatives
Fine-tuned by Writer from Qwen2.5-1.5B, a base model in Alibaba Cloud's Qwen family.178
- 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 v0.1): Open-weight
U.S. eligibility
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.1568
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.