MedErtas-v0.1-31B-LS
基於 Gemma 4 31B 打造
最適合
- 醫學知識與醫療代碼
- 回答檢查
- 辨識無法回答的問題
- 輸出速度
- 189 tokens/s
- 權重
- 24.2 GB,NVFP4
- 草稿模型
- Perigee™
- 授權條款
- Apache-2.0
MedErtas 是為醫療 AI 公司打造的開放權重語言模型系列,專為快速、低成本的推論服務設計。
速度快於基準版本。
準確率高於 MedGemma 27B。
每百萬輸入 token。
基於 Gemma 4 31B 打造
最適合
基於 Qwen3.8-27B 打造
最適合
| 任務 | 31B LS | 27B LS | 領先 | MedGemma 27B參考 |
|---|---|---|---|---|
| 臨床計算MedCalc-Bench 1.2 | 63.9 | 77.3 | 27B LS | 48.6 |
| 搭配工具的計算MedCalc with tools | 61.1 | 76.3 | 27B LS | 無 |
| 醫學知識MedQA | 93.0 | 86.7 | 31B LS | 87.4 |
| 無法回答的問題MetaMedQA | 70.4 | 65.4 | 31B LS | 36.2 |
| 醫療代碼MedConceptsQA,中等與困難的平均值 | 69.8 | 63.2 | 31B LS | 46.4 |
| 回答檢查MedHallu,3 個難度的平均值 | 76.7 | 72.3 | 31B LS | 64.7 |
| 長篇病歷LongHealth,2 項任務的平均值 | 90.0 | 89.0 | 皆可27B 處理長輸入的成本較低 | 81.5 |
開發者可依臨床工作流程調整 MedErtas,並在代理系統中以私有方式執行。
錄製範例保留英文原文,也就是模型執行時使用的語言。
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
錄製的提示詞,temperature 依評估流程設定。請確認你的 API 部署所支援的模型識別碼與請求選項。你的應用程式必須執行計算機工具迴圈。
{
"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.
錄製的提示詞,temperature 依評估流程設定。請確認你的 API 部署所支援的模型識別碼與請求選項。
{
"note": "開啟病歷或複製請求,即可載入完整的原始輸入。",
"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.
錄製的提示詞,temperature 依評估流程設定。請確認你的 API 部署所支援的模型識別碼與請求選項。
{
"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.
MedErtas-v0.1-31B-LS 標示的術語與解說,會在錄製內容審查完成後顯示於此。
同一則提示詞同時傳送給兩個模型。在全精度且不使用草稿模型的情況下,Qwen3.8-27B 需要 5.54 秒才能完成這段 144 token 的答案,速度為 26 tokens/s。MedErtas-v0.1-27B-LS 搭配 Perigee 草稿模型,需要 0.70 秒,速度為 207 tokens/s。
| MedErtas v0.1 31B LS | MedErtas v0.1 27B LS | |
|---|---|---|
| 基準版本 | 22.5 tokens/s | 26 tokens/s |
| 醫療校準權重 | 51 tokens/s2.3x | 60 tokens/s2.3x |
| 推測式草稿模型 | 168 tokens/s3.3x | 188 tokens/s3.1x |
| Perigee™ 醫療草稿模型 | 189 tokens/s+13%基準版本的 8.4x | 207 tokens/s+10%基準版本的 8x |
| 模型 | 輸入 | 快取讀取 | 輸出 |
|---|---|---|---|
| MedErtas-v0.1-31B-LS | $0.20 | $0.05 | $0.60 |
| MedErtas-v0.1-27B-LS | $0.10 | $0.05 | $1.00 |
MedErtas 是 Ertas AI 推出的開放權重醫療語言模型系列。v0.1 版以 Gemma 4 31B 和 Qwen3.8-27B 為基礎,結合領域感知的 4 位元量化與我們的醫療草稿模型 Perigee,提供更快的推論服務。
輸入量大的臨床計算與長篇病歷應用,建議從 MedErtas-v0.1-27B-LS 開始。醫學知識、代碼知識與回答檢查,建議從 MedErtas-v0.1-31B-LS 開始。27B 的輸入價格較低,31B 的輸出價格較低。請用你自己的工作負載評估準確率、延遲與 token 總用量。
模型權重與 Perigee 醫療草稿模型皆以 Apache-2.0 授權發布於 Hugging Face。你可以下載後自行部署。代管 API 是存取模型的選用方式。
Medmarks 排行榜與我們的測試共有 11 項醫療基準測試。在這些測試上,MedErtas 31B 和 27B 的平均分數為 79.6 和 77.1,分別比 MedGemma 27B 在 2026年10月26日排行榜快照中的 63.6 高出 16.0 和 13.5 分。這些是基準測試結果,不是臨床適用性的證據。MedErtas v0.1 僅支援文字,專為快速推論服務打造,採用領域感知量化與 Perigee 醫療草稿模型;MedGemma 另外支援醫學影像理解。MedErtas 採用 Apache-2.0,MedGemma 採用 Health AI Developer Foundations 條款。Ertas 提供按 token 計價的 Beta 版 API,Google 的 Vertex AI 部署則使用專屬端點。請依你的部署方式查閱供應商的最新定價。
可以。權重與 Perigee 草稿模型都能下載。這些權重 採用 NVFP4,可在 NVIDIA Blackwell GPU 上執行。31B 模型的權重為 24.2 GB,另加 1.0 GB 的 Perigee 草稿模型;27B 模型的權重為 22 GB。執行時的記憶體用量取決於你的設定。無論採用自有雲端、本地部署或氣隙環境,都歡迎與我們討論。
每個醫療模型,包括全精度模型,在正式上線前都應整合到經過審慎設計與審查的系統中。MedErtas 的目標是在醫療能力上與全精度基礎模型看齊,同時讓模型的推論服務更快、更便宜,每個版本也都會公布每個受測資料集與全精度的比較結果。其他發布者的壓縮版本仍可能在特定醫療任務上損失準確率。在依賴任何模型之前,請先用你自己的臨床任務,測試它與全精度版本的差異。
LS 是 Lightweight Study(輕量研究)的縮寫,指的是建置規格。LS 版本以領域感知量化壓縮權重,並搭配針對該領域訓練的草稿模型,模型本身的訓練維持不變。後續規格將涵蓋以領域資料再訓練的模型。
Perigee 是 MedErtas 醫療草稿模型的名稱。草稿模型是一種小型輔助模型,會為推測解碼預先提出接下來的數個 token;主模型在一次處理中檢查這些 token,只保留它自己也會產生的部分,因此答案仍遵循主模型,而且產生得更快。MedErtas-v0.1-31B-LS-Perigee 是 Google 的 Gemma 4 31B 輔助草稿模型,以醫療回答微調而成。MedErtas-v0.1-27B-LS-Perigee 是 Red Hat 針對 Qwen3.8-27B 的 DSpark 草稿模型,再以醫療回答進一步訓練而成。兩者皆以 Apache-2.0 授權發布於 Hugging Face,並透過 vLLM 執行。這個名稱取自軌道上最接近被環繞天體的那一點:草稿模型越貼近主模型,被接受的 token 就越多。
高強度或要求穩定的正式環境用途,目前還不行。API 目前為 Beta 版,我們正在完成正式版服務。如果想在自己的硬體上執行,權重已發布在 Hugging Face;如果正在規劃正式環境的用量,歡迎與我們聊聊。
以 Gemma 4 31B 和 Qwen3.8-27B 打造的兩個 LS 版本,各自搭配 Perigee 醫療草稿模型,提供開放權重與代管的 Beta 版 API。
MedErtas 是開發者針對醫療文字打造醫療照護應用程式的起點。在依賴模型之前,每個使用情境都需要開發者各自進行驗證、調整或實質修改。
MedErtas 模型的輸出並非用於直接為臨床診斷、病人管理決策、治療建議或任何其他直接臨床實務提供依據。基準測試結果呈現的是模型在我們列出的測試上的基本能力,而且輸出可能不準確。請將每項輸出視為初步結果:都需要獨立驗證與臨床審查。