MedErtas-v0.1-31B-LS
Basado en Gemma 4 31B
Ideal para
- Conocimiento médico y códigos
- Revisión de respuestas
- Detección de preguntas sin respuesta
- Velocidad de salida
- 189 tokens/s
- Pesos
- 24.2 GB, NVFP4
- Modelo borrador
- Perigee™
- Licencia
- Apache-2.0
MedErtas es una familia de modelos de lenguaje de pesos abiertos para empresas de IA médica, diseñados para una inferencia rápida y de bajo costo.
Más rápido que la línea base.
Más precisión que MedGemma 27B.
Por millón de tokens de entrada.
Basado en Gemma 4 31B
Ideal para
Basado en Qwen3.8-27B
Ideal para
| Tarea | 31B LS | 27B LS | Lidera | MedGemma 27Breferencia |
|---|---|---|---|---|
| Cálculo clínicoMedCalc-Bench 1.2 | 63.9 | 77.3 | 27B LS | 48.6 |
| Cálculo con herramientasMedCalc with tools | 61.1 | 76.3 | 27B LS | N/D |
| Conocimiento médicoMedQA | 93.0 | 86.7 | 31B LS | 87.4 |
| Preguntas sin respuestaMetaMedQA | 70.4 | 65.4 | 31B LS | 36.2 |
| Códigos médicosMedConceptsQA, promedio de los niveles medio y difícil | 69.8 | 63.2 | 31B LS | 46.4 |
| Revisión de respuestasMedHallu, promedio de 3 niveles | 76.7 | 72.3 | 31B LS | 64.7 |
| Historias clínicas largasLongHealth, promedio de 2 tareas | 90.0 | 89.0 | Cualquiera27B cuesta menos con entradas largas | 81.5 |
Los desarrolladores pueden adaptar MedErtas a flujos de trabajo clínicos y ejecutarlo de forma privada dentro de sistemas de agentes.
Responde preguntas sobre historias clínicas largas.
Ver ejemploExtrae variables y calcula puntuaciones clínicas paso a paso.
Ver ejemploRevisa respuestas médicas para detectar afirmaciones sin respaldo.
Ver ejemploExplica en lenguaje sencillo los términos de los informes de radiología.
Ver ejemploLos ejemplos grabados se muestran en inglés, el idioma en el que se ejecutaron.
An 87-year-old man was admitted to our hospital for anorexia for several days, high-grade fever from the previous day, and liver dysfunction. Of note, he had a history of hypertension, diabetes mellitus (DM), and angina. Physical examination findings included: clear consciousness; height, 163 cm; weight, 48 kg; blood pressure, 66/40 mmHg; heart rate, 75/min; respiratory rate, 22/min; oxygen saturation of peripheral artery, 96%; and body temperature, 38.1 °C. He had no surface lymphadenopathy. Laboratory findings included: white blood cell (WBC) count, 4.2 × 109/L; hemoglobin, 9.6 g/dL; platelet count, 106 × 109/L; lactate dehydrogenase (LDH), 1662 IU/L; aspartate aminotransferase (AST), 6562 IU/L; alanine aminotransferase (ALT), 1407 IU/L; alkaline phosphatase (ALP), 509 IU/L; γ-glutamyl transpeptidase (γ-GTP), 130 IU/L; total bilirubin, 2.7 mg/dL; prothrombin time (PT), 20.3 s; international normalized ratio (INR), 1.73; blood urea nitrogen (BUN), 34.4 mg/dL; and creatinine, 1.4 mg/dL. Serologic tests were all negative for hepatitis A, B, C, and E. Computed tomography (CT) performed at admission revealed no distinct nodules or masses in the liver, but mild splenomegaly, multiple hypodense splenic lesions, and para-aortic lymph node swelling (Fig. a–c). Antibiotics were administered intravenously for suspected acute cholangitis and sepsis, but the fever persisted. Abdominal ultrasonography (US) and magnetic resonance imaging (MRI) performed 2 days later newly depicted gallbladder wall thickening and ascites (Figs. , ). On the same night, the patient presented with grade II hepatic encephalopathy, with blood tests showing a decrease in platelet count and worsening liver function suggestive of “acute type” ALF with hepatic coma and disseminated intravascular coagulation (DIC). While consideration was being given to treating acute liver failure, the patient suddenly developed ventricular fibrillation and died despite immediate resuscitation measures on day 3 of hospitalization. Given the rapid clinical course, an autopsy was performed in this patient with suspected ALF likely due to drug-induced liver injury, autoimmune hepatitis, hepatitis of indeterminate etiology, circulatory disturbance, metabolic disease, or malignant cells including malignant lymphoma. This led to the patient being diagnosed with malignant, diffuse large B-cell lymphoma, characterized by multiple lymph-node, as well as multi-organ (i.e., spleen, liver, lung, and prostate) involvement: (1) general swelling of lymph nodes in the para-abdominal aorta (Fig. a), peripancreatic, peribronchial, pulmonary hilar, subclavicular regions, as well as in the pelvis, especially around the iliac arteries, measuring up to 60 mm in diameter; (2) presence of multiple whitish splenic nodules (Fig. b) with the entire spleen shown to be microscopically infiltrated by tumor cells (Fig. a); (3) irregular geographical morphology of the liver (Fig. c) with the lymphoma cells mainly infiltrating the portal areas (Fig. b); (4) involvement of the right lobe of the lung; (5) involvement of both lobes of the prostate consequent to outer connective tissue involvement (Fig. c). Microscopically, the tumor cells in the lymph nodes were shown to have medium-sized irregular nuclei and small nucleoli with a high nuclear cytoplasmic ratio, thus showing diffuse proliferation characterized by the presence of large numbers of small T-cells (Fig. ). Immunohistochemistry revealed the tumor cells to be positive for CD20 (Fig. a), CD79a (Fig. b), bcl-2 (Fig. c), and MUM1 (Fig. d), but negative for CD3 (Fig. e), CD10, bcl-6, and cyclin D1, with a Ki-67 labeling index (Ki-67 LI) of 16% (Fig. f). The causes of death were thus determined as (1) DIC and (2) ALF associated with diffuse large B-cell lymphoma.
What is the patient's Creatinine Clearance using the Cockroft-Gault Equation in terms of mL/min?
I'll calculate the Creatinine Clearance using the Cockcroft-Gault equation.
Step 1: Determine BMI and weight category
Let me extract the values from the patient note: - Age: 87 years - Sex: Male - Height: 163 cm - Weight: 48 kg - Creatinine: 1.4 mg/dL
48 / (1.63 * 1.63)BMI ≈ 18.07, which is underweight (BMI < 18.5).
Per the instructions: "If the patient is underweight, please set their adjusted body weight to their actual body weight."
So adjusted body weight = 48 kg (actual weight).
Step 2: Apply Cockcroft-Gault equation for males:
CrCl = [(140 − age) × weight] / (72 × serum creatinine)
((140 - 87) * 48) / (72 * 1.4)Calculation: - (140 − 87) = 53 - 53 × 48 = 2544 - 72 × 1.4 = 100.8 - 2544 / 100.8 ≈ 25.24 mL/min
Prompt grabado, con la temperatura del protocolo de evaluación. Confirma el identificador del modelo y las opciones de solicitud que admite tu despliegue de la API. Tu aplicación debe ejecutar el bucle de la herramienta de cálculo.
{
"model": "MedErtas-v0.1-27B-LS",
"messages": [
{
"role": "system",
"content": "Please reason step by step, use tools as needed, then give your final answer within <answer>...</answer> XML tags."
},
{
"role": "user",
"content": "You are a helpful assistant. Your task is to read a patient note and compute a medical value based on the following question.\nYou have access to a calculator tool and a python code execution tool. Use them to do any math based on values in the patient note. If using the python tool, make sure the code returns or prints all of its outputs. If there are any errors with compiling or running your script, you may need to re-write your code to obtain the output.\nNote that all of the necessary information is provided in the patient note and you should not need to prompt the user for any information.\nWhen you are finished with all computations, please write your final answer value without any units, using the following formats inside the indicated answer tag:\n\n- Decimal Answer Format: 17.29\n- Score-Based Answer Format: 5\n- Estimated Date Answer Format: 5/21/2021\n- Estimated Age Answer Format: (4 weeks, 3 days)\n\nPatient Note:\n\nAn 87-year-old man was admitted to our hospital for anorexia for several days, high-grade fever from the previous day, and liver dysfunction. Of note, he had a history of hypertension, diabetes mellitus (DM), and angina. Physical examination findings included: clear consciousness; height, 163 cm; weight, 48 kg; blood pressure, 66/40 mmHg; heart rate, 75/min; respiratory rate, 22/min; oxygen saturation of peripheral artery, 96%; and body temperature, 38.1 °C. He had no surface lymphadenopathy. Laboratory findings included: white blood cell (WBC) count, 4.2 × 109/L; hemoglobin, 9.6 g/dL; platelet count, 106 × 109/L; lactate dehydrogenase (LDH), 1662 IU/L; aspartate aminotransferase (AST), 6562 IU/L; alanine aminotransferase (ALT), 1407 IU/L; alkaline phosphatase (ALP), 509 IU/L; γ-glutamyl transpeptidase (γ-GTP), 130 IU/L; total bilirubin, 2.7 mg/dL; prothrombin time (PT), 20.3 s; international normalized ratio (INR), 1.73; blood urea nitrogen (BUN), 34.4 mg/dL; and creatinine, 1.4 mg/dL. Serologic tests were all negative for hepatitis A, B, C, and E. Computed tomography (CT) performed at admission revealed no distinct nodules or masses in the liver, but mild splenomegaly, multiple hypodense splenic lesions, and para-aortic lymph node swelling (Fig. a–c). Antibiotics were administered intravenously for suspected acute cholangitis and sepsis, but the fever persisted. Abdominal ultrasonography (US) and magnetic resonance imaging (MRI) performed 2 days later newly depicted gallbladder wall thickening and ascites (Figs. , ). On the same night, the patient presented with grade II hepatic encephalopathy, with blood tests showing a decrease in platelet count and worsening liver function suggestive of “acute type” ALF with hepatic coma and disseminated intravascular coagulation (DIC). While consideration was being given to treating acute liver failure, the patient suddenly developed ventricular fibrillation and died despite immediate resuscitation measures on day 3 of hospitalization.\nGiven the rapid clinical course, an autopsy was performed in this patient with suspected ALF likely due to drug-induced liver injury, autoimmune hepatitis, hepatitis of indeterminate etiology, circulatory disturbance, metabolic disease, or malignant cells including malignant lymphoma. This led to the patient being diagnosed with malignant, diffuse large B-cell lymphoma, characterized by multiple lymph-node, as well as multi-organ (i.e., spleen, liver, lung, and prostate) involvement: (1) general swelling of lymph nodes in the para-abdominal aorta (Fig. a), peripancreatic, peribronchial, pulmonary hilar, subclavicular regions, as well as in the pelvis, especially around the iliac arteries, measuring up to 60 mm in diameter; (2) presence of multiple whitish splenic nodules (Fig. b) with the entire spleen shown to be microscopically infiltrated by tumor cells (Fig. a); (3) irregular geographical morphology of the liver (Fig. c) with the lymphoma cells mainly infiltrating the portal areas (Fig. b); (4) involvement of the right lobe of the lung; (5) involvement of both lobes of the prostate consequent to outer connective tissue involvement (Fig. c). Microscopically, the tumor cells in the lymph nodes were shown to have medium-sized irregular nuclei and small nucleoli with a high nuclear cytoplasmic ratio, thus showing diffuse proliferation characterized by the presence of large numbers of small T-cells (Fig. ). Immunohistochemistry revealed the tumor cells to be positive for CD20 (Fig. a), CD79a (Fig. b), bcl-2 (Fig. c), and MUM1 (Fig. d), but negative for CD3 (Fig. e), CD10, bcl-6, and cyclin D1, with a Ki-67 labeling index (Ki-67 LI) of 16% (Fig. f). The causes of death were thus determined as (1) DIC and (2) ALF associated with diffuse large B-cell lymphoma.\n\nQuestion:\n\nWhat is the patient's Creatinine Clearance using the Cockroft-Gault Equation in terms of mL/min? You should use the patient's adjusted body weight in kg instead of the patient's actual body weight if the patient is overweight or obese based on their BMI. If the patient's BMI's normal, set their adjusted body weight to the minimum of the ideal body and actual weight. If the patient is underweight, please set their adjusted body weight to their actual body weight. You should use the patient's medical values and health status when they were first admitted to the hospital prior to any treatment."
}
],
"temperature": 1,
"chat_template_kwargs": {
"enable_thinking": false
},
"tools": [
{
"type": "function",
"function": {
"name": "calculator",
"description": "Evaluate a mathematical expression safely.\n\nSupports basic arithmetic (+, -, *, /, %, **), parentheses, and common math functions. Use ^ or ** for exponentiation.\n\nAvailable functions: sqrt, sin, cos, tan, log, log10, exp, abs, round\nAvailable constants: pi, e",
"parameters": {
"properties": {
"expression": {
"description": "A mathematical expression to evaluate.",
"title": "Expression",
"type": "string"
}
},
"required": [
"expression"
],
"title": "calculator_args",
"type": "object",
"additionalProperties": false
},
"strict": null
}
},
{
"type": "function",
"function": {
"name": "code_interpreter",
"description": "Execute Python code in a sandboxed REPL environment. Variables persist across calls.\n\nThis is a restricted environment - file I/O and network access are disabled.\nAllowed imports: math, numpy, scipy. Pre-loaded: numpy (as np), math, scipy. Use print() to display results.",
"parameters": {
"properties": {
"code": {
"description": "A block of Python code to execute.",
"title": "Code",
"type": "string"
}
},
"required": [
"code"
],
"title": "code_interpreter_args",
"type": "object",
"additionalProperties": false
},
"strict": null
}
}
]
}Initiated R-Pola-CHP regimen q21
Which of the following is NOT part of the current treatment regimen for Mrs. Sample's DLBCL?
The correct answer is D: Vincristine.
Prompt grabado, con la temperatura del protocolo de evaluación. Confirma el identificador del modelo y las opciones de solicitud que admite tu despliegue de la API.
{
"note": "Abre la historia clínica o copia la solicitud para cargar la entrada original completa.",
"model": "MedErtas-v0.1-31B-LS",
"temperature": 1
}Double balloon enteroscopy: is it efficacious and safe in a community setting?
DBE shows slightly higher complication rates in the community setting due to less experienced staff performing the procedure.
The provided answer makes a generalization that double balloon enteroscopy (DBE) has "slightly higher complication rates in the community setting due to less experienced staff." In medical literature, studies comparing DBE in community settings versus tertiary academic centers generally indicate that DBE is safe and efficacious in both environments, with complication rates remaining low and comparable across settings when performed by trained endoscopists. There is no established medical consensus or consistent evidence that community settings inherently have higher complication rates due to staff experience.
Therefore, the answer provides a claim that is not supported by established clinical evidence and attributes a cause (staff experience) that contradicts the general finding that the procedure is safe in community settings.
Prompt grabado, con la temperatura del protocolo de evaluación. Confirma el identificador del modelo y las opciones de solicitud que admite tu despliegue de la API.
{
"model": "MedErtas-v0.1-31B-LS",
"messages": [
{
"role": "system",
"content": "\nYou are an AI assistant with extensive knowledge in the field of medicine. I want you act as an answer judge. Given a question and an answer, your objective is to determine if the provided answer contains non-factual or hallucinated information. You SHOULD give your judgement based on the following hallucination types and the world knowledge.\n\nType: Misinterpretation of #Question#: These are hallucinated answers that misunderstands the question, leading to an off-topic or irrelevant response.\nType: Incomplete Information: These are hallucinated answers that Point out what is not true without providing correct information.\nType: Mechanism and Pathway Misattribution - These are hallucinated answer that falsely attribution of biological mechanisms, molecular pathways, or disease processes that contradicts established medical knowledge\nType: Methodological and Evidence Fabrication - Inventing false research methods, statistical data, or specific clinical outcomes\n\n\nYou are trying to determine if there is a factual contradiction between the answer and the world knowledge.\nSome information in the answer might be fabricated. Answer \\boxed{{0}} if the answer is factual and \\boxed{{1}} if the answer is hallucinated and \\boxed{{2}} if you are unsure about the factuality and want to pass. If you are unsure about the answer choose \\boxed{{2}} instead of guessing and making a mistake.\n"
},
{
"role": "user",
"content": "\nQuestion: Double balloon enteroscopy: is it efficacious and safe in a community setting?\nAnswer: DBE shows slightly higher complication rates in the community setting due to less experienced staff performing the procedure.\n\nReturn just the answer, Answer \\boxed{0} if the answer is factual and \\boxed{1} if the answer is hallucinated and \\boxed{2} if you are unsure about the answer and want to pass.\nIf you are unsure about the answer choose \\boxed{2} instead of guessing and making a mistake.\nYour Judgement:\n"
}
],
"temperature": 1,
"chat_template_kwargs": {
"enable_thinking": false
}
}Indication: Persistent cough. No prior imaging available for comparison. Technique: Non-contrast CT of the chest with multiplanar reformats. Findings: A solitary 5 mm solid nodule is present in the peripheral right upper lobe. No focal air-space consolidation. No pleural effusion or pneumothorax. Central airways are patent. No enlarged mediastinal lymph nodes by CT size criteria. No acute osseous abnormality in the imaged chest. Impression: Solitary 5 mm right upper lobe pulmonary nodule. No prior study is available to assess stability. No acute air-space disease.
Los términos resaltados y sus explicaciones de MedErtas-v0.1-31B-LS aparecerán aquí cuando se haya revisado la ejecución grabada.
El mismo prompt llega a ambos modelos. A precisión completa y sin modelo borrador, Qwen3.8-27B tarda 5.54 segundos en dar la respuesta de 144 tokens, a 26 tokens/s. MedErtas-v0.1-27B-LS con el modelo borrador Perigee tarda 0.70 segundos, a 207 tokens/s.
| MedErtas v0.1 31B LS | MedErtas v0.1 27B LS | |
|---|---|---|
| Línea base | 22.5 tokens/s | 26 tokens/s |
| Pesos calibrados para medicina | 51 tokens/s2.3x | 60 tokens/s2.3x |
| Modelo borrador especulativo | 168 tokens/s3.3x | 188 tokens/s3.1x |
| Modelo borrador médico Perigee™ | 189 tokens/s+13%8.4x la línea base | 207 tokens/s+10%8x la línea base |
| Modelo | Entrada | Lectura de caché | Salida |
|---|---|---|---|
| MedErtas-v0.1-31B-LS | $0.20 | $0.05 | $0.60 |
| MedErtas-v0.1-27B-LS | $0.10 | $0.05 | $1.00 |
MedErtas es una familia de modelos de lenguaje médicos de pesos abiertos de Ertas AI. El lanzamiento v0.1 se basa en Gemma 4 31B y Qwen3.8-27B, y combina una cuantización de 4 bits adaptada al dominio con Perigee, nuestros modelos borrador médicos, para una inferencia más rápida.
Empieza con MedErtas-v0.1-27B-LS para cálculo clínico y aplicaciones con historias clínicas largas y entradas grandes. Empieza con MedErtas-v0.1-31B-LS para conocimiento médico, conocimiento de códigos y revisión de respuestas. El 27B tiene un precio de entrada más bajo; el 31B, un precio de salida más bajo. Evalúa la precisión, la latencia y el uso total de tokens con tu propia carga de trabajo.
Los pesos del modelo y los modelos borrador médicos Perigee se publican bajo Apache-2.0 en Hugging Face. Puedes descargarlos y ejecutar tu propio despliegue. La API alojada es una forma opcional de acceder a los modelos.
En los 11 benchmarks médicos que la clasificación de Medmarks comparte con nuestras ejecuciones, MedErtas 31B y 27B promedian 79.6 y 77.1, 16.0 y 13.5 puntos por encima de los 63.6 de MedGemma 27B en la instantánea de la clasificación del 26 de octubre de 2026. Son resultados de benchmarks, no evidencia de idoneidad clínica. MedErtas v0.1 solo trabaja con texto y está diseñado para una inferencia rápida, con cuantización adaptada al dominio y modelos borrador médicos Perigee; MedGemma también admite la comprensión de imágenes médicas. MedErtas usa Apache-2.0, y MedGemma usa los términos de Health AI Developer Foundations. Ertas ofrece una API beta con precio por token, mientras que el despliegue de Google en Vertex AI usa un endpoint dedicado. Consulta los precios vigentes del proveedor para tu despliegue.
Sí. Los pesos y los modelos borrador Perigee se pueden descargar. Los pesos usan NVFP4, que funciona en GPUs NVIDIA Blackwell. Los pesos del modelo 31B ocupan 24.2 GB, más los 1.0 GB del modelo borrador Perigee; los del modelo 27B ocupan 22 GB. La memoria en ejecución depende de tu configuración. Hablemos de tu despliegue en tu propia nube, on-premise o air-gapped.
Todo modelo médico, incluso a precisión completa, debe integrarse en un sistema cuidadosamente diseñado y revisado antes de usarse en producción. MedErtas busca igualar en capacidad médica a su base de precisión completa, a la vez que hace el modelo más rápido y más económico de servir, y cada lanzamiento publica la comparación con la precisión completa en cada conjunto que evaluamos. Las versiones comprimidas de terceros todavía pueden perder precisión en determinadas tareas médicas. Prueba cualquier modelo frente a la precisión completa en tus propias tareas clínicas antes de confiar en él.
LS, de Lightweight Study (estudio ligero), es el perfil de la versión. Una versión LS comprime los pesos con cuantización adaptada al dominio y los combina con un modelo borrador entrenado en el dominio, sin cambiar el entrenamiento original del modelo. Los perfiles futuros abarcarán modelos con entrenamiento posterior en datos del dominio.
Perigee es el nombre de los modelos borrador médicos de MedErtas. Un modelo borrador es un pequeño modelo auxiliar que propone varios tokens por adelantado para la decodificación especulativa; el modelo principal los verifica en una sola pasada y conserva solo los tokens que él mismo produciría, de modo que las respuestas siguen al modelo principal y llegan más rápido. MedErtas-v0.1-31B-LS-Perigee es el modelo borrador asistente de Gemma 4 31B de Google, ajustado con respuestas médicas. MedErtas-v0.1-27B-LS-Perigee es el modelo borrador DSpark de Red Hat para Qwen3.8-27B, con entrenamiento adicional en respuestas médicas. Ambos se publican bajo Apache-2.0 en Hugging Face y se ejecutan con vLLM. El nombre viene del punto de una órbita más cercano al cuerpo que rodea: cuanto más de cerca sigue un modelo borrador al modelo principal, más tokens suyos se aceptan.
Todavía no para un uso intensivo o estable en producción. La API está en beta mientras terminamos la oferta de producción. Los pesos están en Hugging Face si quieres ejecutarlos en tu propio hardware, y si planificas volúmenes de producción, hablemos.
Dos versiones LS a partir de Gemma 4 31B y Qwen3.8-27B, cada una con su modelo borrador médico Perigee, pesos abiertos y una API beta alojada.
MedErtas es un punto de partida para desarrolladores que crean aplicaciones de salud sobre texto médico. Cada caso de uso necesita su propia validación, adaptación o modificación significativa por parte del desarrollador antes de confiar en el modelo.
Las salidas de los modelos MedErtas no están destinadas a informar directamente el diagnóstico clínico, las decisiones de manejo del paciente, las recomendaciones de tratamiento ni ninguna otra práctica clínica directa. Los resultados de los benchmarks muestran la capacidad de base en las pruebas que nombramos, y las salidas pueden ser inexactas. Trata cada salida como preliminar: necesita verificación independiente y revisión clínica.
¿Planificas volúmenes de producción? Hablemos