This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
Open-weight model · Summarization
Medra27B-i1-GGUF
by Team Mradermacher mradermacher/Medra27B-i1-GGUF
weighted/imatrix quants of https://huggingface.co/nicoboss/Medra27B For a convenient overview and download list, visit our model page for this model.
Parameters—
Context—
Weights294.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.9k
Model Card
By Team Mradermacher, published under apache-2.0, revision 946155835df3.
weighted/imatrix quants of https://huggingface.co/nicoboss/Medra27B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Medra27B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
Read Team Mradermacher's full model card
About
weighted/imatrix quants of https://huggingface.co/nicoboss/Medra27B
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Medra27B-GGUF
This is a vision model - mmproj files (if any) will be in the static repository.
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | i1-IQ1_S | 6.4 | for the desperate |
| GGUF | i1-IQ1_M | 6.9 | mostly desperate |
| GGUF | i1-IQ2_XXS | 7.8 | |
| GGUF | i1-IQ2_XS | 8.5 | |
| GGUF | i1-IQ2_S | 8.9 | |
| GGUF | i1-IQ2_M | 9.6 | |
| GGUF | i1-Q2_K_S | 9.9 | very low quality |
| GGUF | i1-Q2_K | 10.6 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 10.8 | lower quality |
| GGUF | i1-IQ3_XS | 11.7 | |
| GGUF | i1-IQ3_S | 12.3 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 12.6 | |
| GGUF | i1-Q3_K_M | 13.5 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 14.6 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 14.9 | |
| GGUF | i1-Q4_0 | 15.7 | fast, low quality |
| GGUF | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 16.6 | fast, recommended |
| GGUF | i1-Q4_1 | 17.3 | |
| GGUF | i1-Q5_K_S | 18.9 | |
| GGUF | i1-Q5_K_M | 19.4 | |
| GGUF | i1-Q6_K | 22.3 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
Identity and Version
- Repository
- mradermacher/Medra27B-i1-GGUF
- Publisher
- Team Mradermacher
- Task
- Summarization
- Modality
- Text
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- en, ro
- Revision
- 946155835df3ed7f193b014fcb13247d12f7aa20
- First published
- 2025-05-30
- Last updated
- 2026-01-26
Files and Weights
26 files, 294.9 GB in total. The weights are 23 files totalling 294.8 GB in gguf.
Weights23 files · 294.8 GB
Documentation1 file · 5.3 KB
Other1 file · 13.0 MB
Repository1 file · 2.9 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Medra27B.i1-IQ1_M.gguf | Weights | 6.8 GB | 5badcf5d0093 |
| Medra27B.i1-IQ1_S.gguf | Weights | 6.3 GB | 2310c039189e |
| Medra27B.i1-IQ2_M.gguf | Weights | 9.5 GB | f3e8819febee |
| Medra27B.i1-IQ2_S.gguf | Weights | 8.8 GB | 8cebaf83f122 |
| Medra27B.i1-IQ2_XS.gguf | Weights | 8.4 GB | 863fddc574de |
| Medra27B.i1-IQ2_XXS.gguf | Weights | 7.7 GB | bee59d2de12e |
| Medra27B.i1-IQ3_M.gguf | Weights | 12.5 GB | 818c0b4db68a |
| Medra27B.i1-IQ3_S.gguf | Weights | 12.2 GB | 5a1edf00974f |
| Medra27B.i1-IQ3_XS.gguf | Weights | 11.6 GB | 2932c0e7727e |
| Medra27B.i1-IQ3_XXS.gguf | Weights | 10.7 GB | cf93734c74b2 |
| Medra27B.i1-IQ4_XS.gguf | Weights | 14.8 GB | bdd0ade08fbe |
| Medra27B.i1-Q2_K.gguf | Weights | 10.5 GB | 552700d7129e |
| Medra27B.i1-Q2_K_S.gguf | Weights | 9.8 GB | 8c7520878666 |
| Medra27B.i1-Q3_K_L.gguf | Weights | 14.5 GB | 04403f545663 |
| Medra27B.i1-Q3_K_M.gguf | Weights | 13.4 GB | f0c02073577f |
| Medra27B.i1-Q3_K_S.gguf | Weights | 12.2 GB | e5453c9437a9 |
| Medra27B.i1-Q4_0.gguf | Weights | 15.6 GB | 9dfc10446d1d |
| Medra27B.i1-Q4_1.gguf | Weights | 17.2 GB | b94679564464 |
| Medra27B.i1-Q4_K_M.gguf | Weights | 16.5 GB | 1f51588c776b |
| Medra27B.i1-Q4_K_S.gguf | Weights | 15.7 GB | dc3430c35eee |
| Medra27B.i1-Q5_K_M.gguf | Weights | 19.3 GB | adc2b94e2b72 |
| Medra27B.i1-Q5_K_S.gguf | Weights | 18.8 GB | 68a4e92fe5b4 |
| Medra27B.i1-Q6_K.gguf | Weights | 22.2 GB | 299f5845ef82 |
| README.md | Documentation | 5.3 KB | — |
| imatrix.dat | Other | 13.0 MB | f54c88aa12d0 |
| .gitattributes | Repository | 2.9 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 294.8 GB
Download from Team Mradermacher
Released by Team Mradermacher through its official repository on Hugging Face. Read the license.
Built From
- Derived from nicoboss/Medra27B
- Quantized from nicoboss/Medra27B
- Trained on (disclosed) nicoboss/medra-medical
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 294.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Medra27B-i1-GGUF
Can I use Medra27B-i1-GGUF commercially?
Yes. Medra27B-i1-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Original TF 1 code here Authors: Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu on Dec 18, 2019 The following is copied from the authors' README. We train a pegasus model with sampled gap sentence ratios on both C4 and HugeNews, and stochastically sample important sentences. The updated the results are reported in this table. The "Mixed & Stochastic" model has the following changes: - trained on both C4 and HugeNews (dataset mixture is weighted by their number of examples). - trained for 1.5M instead of 500k (we observe slower convergence on pretraining perplexity). - the model uniformly sample a gap sentence ratio between 15% and 45%. - importance sentences are sampled using a…
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
This repository contains the mT5 checkpoint finetuned on the 45 languages of XL-Sum dataset. For finetuning details and scripts, see the paper and the official repository. Scores on the XL-Sum test sets are as follows: Language | ROUGE-1 / ROUGE-2 / ROUGE-L Amharic | 20.0485 / 7.4111 / 18.0753 Arabic | 34.9107 / 14.7937 / 29.1623 Azerbaijani | 21.4227 / 9.5214 / 19.3331 Bengali | 29.5653 / 12.1095 / 25.1315 Burmese | 15.9626 / 5.1477 / 14.1819 Chinese (Simplified) | 39.4071 / 17.7913 / 33.406 Chinese (Traditional) | 37.1866 / 17.1432 / 31.6184 English | 37.601 / 15.1536 / 29.8817 French | 35.3398 / 16.1739 / 28.2041 Gujarati | 21.9619 / 7.7417 / 19.86 Hausa | 39.4375 / 17.6786 / 31.6667…