{"id":14865,"date":"2026-08-24T14:35:21","date_gmt":"2026-08-24T18:35:21","guid":{"rendered":"https:\/\/labs.icahn.mssm.edu\/minervalab\/?page_id=14865"},"modified":"2026-08-24T16:00:55","modified_gmt":"2026-08-24T20:00:55","slug":"ai-models","status":"publish","type":"page","link":"https:\/\/labs.icahn.mssm.edu\/minervalab\/documentation\/ollama\/ai-models\/","title":{"rendered":"AI Models"},"content":{"rendered":"

[et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”4.16″ custom_padding=”0px||0px||false|false” global_colors_info=”{}”][et_pb_row admin_label=”row” _builder_version=”4.16″ custom_padding=”||0px||false|false” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text admin_label=”Breadcrumb” _builder_version=”4.16″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Scientific Computing and Data<\/a>\u00a0\/\u00a0High Performance Computing<\/a> \/ Documentation<\/a> \/ Ollama<\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”][et_pb_row _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” hover_enabled=”0″ custom_css_free_form=”.minerva-doc {|| –ink-900: #212070;|| –ink-700: #3a3a52;|| –ink-500: #6f7086;|| –line: #e4e4ee;|| –line-soft: #efeff6;|| –bg-page: #fbfbfd;|| –bg-card: #ffffff;|| –bg-subtle: #f5f5fa;|| –accent-600: #dc298d;|| –accent-500: #dc298d;|| –accent-100: #fbdeee;|| –accent-050: #fdf0f7;|| –indigo-100: #e4e4f2;|| –indigo-050: #f2f2f9;|| –code-bg: #1b1b3a;|| –code-text: #e6e6f0;|| –code-line: rgba(255, 255, 255, 0.08);|| –font-body: %22Open Sans%22, -apple-system, BlinkMacSystemFont, %22Segoe UI%22, Helvetica, Arial, sans-serif;|| –font-mono: %22SFMono-Regular%22, %22JetBrains Mono%22, Consolas, Menlo, monospace;|| –radius-lg: 14px;|| –radius-md: 8px;|| width: 100%;|| padding: 0 8px;|| background: var(–bg-page);|| color: var(–ink-700);|| font-family: var(–font-body);|| font-size: 16px;|| line-height: 1.65;|| -webkit-font-smoothing: antialiased;||}||||.minerva-doc *,||.minerva-doc *::before,||.minerva-doc *::after {|| box-sizing: border-box;||}||||.minerva-doc p br,||.minerva-doc li br,||.minerva-doc .note br,||.minerva-doc .callout br {|| display: none;||}||||.minerva-doc .site-header {|| padding: 40px 0 8px;||}||||.minerva-doc .brand-tag {|| display: inline-flex;|| align-items: center;|| font-size: 12.5px;|| font-weight: 600;|| color: #212070;|| background: var(–indigo-100);|| padding: 5px 12px;|| border-radius: 999px;|| letter-spacing: 0.2px;|| margin-bottom: 14px;||}||||.minerva-doc .brand-title {|| margin: 0;|| color: var(–ink-900);|| font-size: 32px;|| font-weight: 700;|| letter-spacing: -0.6px;|| line-height: 1.2;||}||||.minerva-doc .intro {|| padding: 14px 0 30px;|| border-bottom: 1px solid var(–line);||}||||.minerva-doc .doc-section {|| border-bottom: 1px solid var(–line);||}||||.minerva-doc .doc-section:last-of-type {|| border-bottom: none;||}||||.minerva-doc .doc-section summary {|| list-style: none;|| cursor: pointer;|| padding: 22px 0;|| display: flex;|| align-items: baseline;|| gap: 8px;|| font-size: 26px;|| font-weight: 700;|| color: var(–ink-900);|| position: relative;||}||||.minerva-doc .doc-section summary::-webkit-details-marker {|| display: none;||}||||.minerva-doc .doc-section summary::after {|| content: %22%22;|| margin-left: auto;|| align-self: center;|| width: 10px;|| height: 10px;|| border-right: 2px solid var(–ink-500);|| border-bottom: 2px solid var(–ink-500);|| transform: rotate(45deg);|| transition: transform 0.2s ease;|| flex: none;||}||||.minerva-doc .doc-section%91open%93 summary::after {|| transform: rotate(-135deg);|| border-color: var(–accent-600);||}||||.minerva-doc .doc-section summary:hover {|| color: var(–accent-600);||}||||.minerva-doc .section-body {|| padding: 16px 0 28px;||}||||.minerva-doc .intro-eyebrow {|| display: block;|| font-family: var(–font-body);|| font-size: 26px;|| font-weight: 700;|| color: var(–ink-900);|| letter-spacing: 0;|| margin-bottom: 10px;||}||||.minerva-doc p {|| margin: 0 0 16px;|| color: var(–ink-700);||}||||.minerva-doc a {|| color: var(–accent-600);|| text-decoration: none;|| background-image: linear-gradient(var(–accent-500), var(–accent-500));|| background-repeat: no-repeat;|| background-size: 100% 1px;|| background-position: 0 100%;||}||||.minerva-doc a:hover {|| color: var(–ink-900);|| background-image: linear-gradient(#212070, #212070);||}||||.minerva-doc strong {|| font-weight: 600;|| color: var(–ink-900);||}||||.minerva-doc ul,||.minerva-doc ol {|| margin: 0 0 16px;|| padding-left: 22px;||}||||.minerva-doc li {|| margin-bottom: 9px;||}||||.minerva-doc li ul,||.minerva-doc li ol {|| margin-top: 9px;|| margin-bottom: 0;||}||||.minerva-doc ul > li::marker {|| color: var(–accent-500);||}||||.minerva-doc ol > li::marker {|| color: var(–accent-500);|| font-weight: 600;||}||||.minerva-doc .callout {|| margin: 20px 0 16px;|| padding: 18px 22px;|| border-radius: var(–radius-md);||}||||.minerva-doc .callout-accent {|| background: var(–indigo-050);|| border: 1px solid var(–indigo-100);|| border-left: 3px solid var(–accent-500);||}||||.minerva-doc code {|| font-family: var(–font-mono);|| background: var(–bg-subtle);|| color: #b81f77;|| padding: 2px 6px;|| border-radius: 4px;|| font-size: 0.87em;|| border: 1px solid var(–line);||}||||.minerva-doc .code-block {|| background: var(–code-bg);|| border-radius: var(–radius-md);|| margin: 14px 0 22px;|| overflow: hidden;|| box-shadow: 0 8px 24px rgba(33, 32, 112, 0.18);||}||||.minerva-doc .code-block-header {|| display: flex;|| align-items: center;|| gap: 6px;|| padding: 8px 10px 8px 14px;|| border-bottom: 1px solid var(–code-line);||}||||.minerva-doc .code-lang {|| font-family: var(–font-mono);|| font-size: 11px;|| color: #9b9bc0;|| text-transform: uppercase;|| letter-spacing: 1px;||}||||.minerva-doc .code-block pre {|| margin: 0;|| padding: 16px 18px 18px;|| font-family: var(–font-mono);|| font-size: 13.5px;|| line-height: 1.7;|| color: var(–code-text);|| white-space: pre-wrap;|| word-break: break-word;|| overflow-x: auto;||}||||.minerva-doc .code-block pre code {|| background: none;|| border: none;|| padding: 0;|| color: inherit;||}||||.minerva-doc .table-wrap {|| overflow-x: auto;|| margin: 14px 0 16px;|| border-radius: var(–radius-md);|| border: 1px solid var(–line);||}||||.minerva-doc table {|| width: 100%;|| border-collapse: collapse;|| font-size: 14px;||}||||.minerva-doc th {|| background: var(–indigo-050);|| color: var(–ink-900);|| font-weight: 600;|| text-align: left;|| padding: 12px 16px;|| font-size: 12px;|| text-transform: uppercase;|| letter-spacing: 0.5px;|| border-bottom: 1px solid var(–indigo-100);||}||||.minerva-doc td {|| padding: 12px 16px;|| border-top: 1px solid var(–line-soft);|| vertical-align: top;|| color: var(–ink-700);||}||||.minerva-doc tbody tr:hover {|| background: var(–bg-subtle);||}||||.minerva-doc .sub-section {|| border-top: 1px solid var(–line-soft);|| margin-top: 6px;||}||||.minerva-doc .sub-section:first-of-type {|| border-top: none;|| margin-top: 0;||}||||.minerva-doc .sub-section summary {|| list-style: none;|| cursor: pointer;|| padding: 14px 0;|| display: flex;|| align-items: baseline;|| gap: 8px;|| font-size: 15px;|| font-weight: 600;|| color: var(–ink-900);|| position: relative;||}||||.minerva-doc .sub-section summary::-webkit-details-marker {|| display: none;||}||||.minerva-doc .sub-section summary::after {|| content: %22%22;|| margin-left: auto;|| align-self: center;|| width: 8px;|| height: 8px;|| border-right: 2px solid var(–ink-500);|| border-bottom: 2px solid var(–ink-500);|| transform: rotate(45deg);|| transition: transform 0.2s ease;|| flex: none;||}||||.minerva-doc .sub-section%91open%93 summary::after {|| transform: rotate(-135deg);|| border-color: var(–accent-600);||}||||.minerva-doc .sub-section summary:hover {|| color: var(–accent-600);||}||||.minerva-doc .sub-body {|| padding: 0 0 20px;||}||||.minerva-doc .sub-body > *:last-child {|| margin-bottom: 0;||}||||.minerva-doc .doc-footer {|| padding: 24px 0 8px;|| text-align: center;|| color: var(–ink-500);|| font-size: 13px;||}||||@media (max-width: 520px) {|| .minerva-doc .brand-title { font-size: 24px; }|| .minerva-doc .doc-section summary { font-size: 21px; }|| .minerva-doc .intro-eyebrow { font-size: 21px; }||}” global_colors_info=”{}” sticky_enabled=”0″]<\/p>\n

\n
\n

HPC Documentation<\/span><\/p>\n

 <\/p>\n

Minerva Generative Assistant Tool: Supported AI Models<\/h1>\n<\/div>\n
\n

Model Catalog<\/span><\/p>\n

This page provides a reference for all Large Language Models (LLMs) deployed on the Minerva HPC Generative AI Assistant infrastructure. All models run on local GPU clusters (NVIDIA H100s) ensuring institutional privacy with zero external telemetry.<\/p>\n

\u2190 Return to Minerva AI Assistant Overview & Usage Guide<\/a><\/div>\n<\/div>\n
\n
\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Model<\/th>\nParameters<\/th>\nBest For<\/th>\nMore Information<\/th>\n<\/tr>\n<\/thead>\n
gemma3:4b<\/code><\/td>\n4B<\/td>\nLightweight multimodal model for fast text and image tasks<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:12b-it-fp16<\/code><\/td>\n12B<\/td>\nFull-precision Gemma 3 model for high-quality text and vision tasks<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:12b-it-q8_0<\/code><\/td>\n12B<\/td>\nHigh-precision 8-bit quantized Gemma 3 model for multimodal reasoning<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:12b-it-q4_K_M<\/code><\/td>\n12B<\/td>\nBalanced 4-bit quantized Gemma 3 12B for resource-efficient performance<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:12b-it-qat<\/code><\/td>\n12B<\/td>\nQuantization-Aware Trained 12B model balancing low memory and high quality<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:27b-it-fp16<\/code><\/td>\n27B<\/td>\nFull-precision high-capacity model for complex multimodal reasoning<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:27b-it-q8_0<\/code><\/td>\n27B<\/td>\n8-bit quantized Gemma 3 27B for precise instruction following & vision tasks<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:27b-it-q4_K_M<\/code><\/td>\n27B<\/td>\n4-bit quantized Gemma 3 27B offering strong reasoning with low VRAM footprint<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma3:27b-it-qat<\/code><\/td>\n27B<\/td>\nQuantization-Aware Trained 27B model delivering near-BF16 precision<\/td>\nGoogle Gemma 3<\/a><\/td>\n<\/tr>\n
gemma4:26b<\/code><\/td>\n26B<\/td>\nHigh-performance Gemma 4 model for deep reasoning and analytical tasks<\/td>\nGoogle Gemma 4<\/a><\/td>\n<\/tr>\n
gemma4:31b<\/code><\/td>\n31B<\/td>\nNext-gen Gemma 4 model for advanced multimodal and complex logic workflows<\/td>\nGoogle Gemma 4<\/a><\/td>\n<\/tr>\n
gpt-oss:20b<\/code><\/td>\n21B<\/td>\nOpen-weight model optimized for fast reasoning and function calling<\/td>\nOpenAI GPT-OSS<\/a><\/td>\n<\/tr>\n
gpt-oss:120b<\/code><\/td>\n117B<\/td>\nLarge open-weight model for enterprise-grade reasoning and agent workflows<\/td>\nOpenAI GPT-OSS<\/a><\/td>\n<\/tr>\n
llama3.3:70b<\/code><\/td>\n71B<\/td>\nBest-in-class reasoning, handles complex queries, lowest hallucination rate<\/td>\nMeta Llama 3.3<\/a><\/td>\n<\/tr>\n
llama4:latest<\/code><\/td>\n109B<\/td>\nFlagship Mixture-of-Experts multimodal model for complex reasoning and chat<\/td>\nMeta Llama 4<\/a><\/td>\n<\/tr>\n
llava:7b<\/code><\/td>\n7B<\/td>\nMultimodal vision-language model (image + text)<\/td>\nLLaVA GitHub<\/a><\/td>\n<\/tr>\n
medgemma1.5:latest<\/code><\/td>\n4B<\/td>\nDomain-specific clinical reasoning and medical text understanding<\/td>\nGoogle MedGemma<\/a><\/td>\n<\/tr>\n
muse-glimmer:latest<\/code><\/td>\n28B<\/td>\nAgentic model optimized for multi-step reasoning, tool use, and long-horizon tasks<\/td>\nMeta Muse Glimmer<\/a><\/td>\n<\/tr>\n
nemotron-3-nano:30b<\/code><\/td>\n32B<\/td>\nGPU-optimized architecture for fast enterprise language generation<\/td>\nNVIDIA Nemotron<\/a><\/td>\n<\/tr>\n
phi4:latest<\/code><\/td>\n15B<\/td>\nHigh-efficiency small model with strong reasoning, math, and coding skills<\/td>\nMicrosoft Phi-4<\/a><\/td>\n<\/tr>\n
tinyllama:latest<\/code><\/td>\n1B<\/td>\nLightweight, fast inference with minimal resource footprint<\/td>\nTinyLlama GitHub<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n
Note:<\/strong> LLM models available in the Assistant tool may make mistakes. Always review outputs carefully before using them.<\/div>\n<\/div>\n
Minerva HPC Documentation \u2014 AI Assistant Tool<\/div>\n<\/div>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"

Scientific Computing and Data\u00a0\/\u00a0High Performance Computing \/ Documentation \/ Ollama HPC Documentation   Minerva Generative Assistant Tool: Supported AI Models Model Catalog This page provides a reference for all Large Language Models (LLMs) deployed on the Minerva HPC Generative AI Assistant infrastructure. All models run on local GPU clusters (NVIDIA H100s) ensuring institutional privacy with […]<\/p>\n","protected":false},"author":624,"featured_media":0,"parent":8189,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"class_list":["post-14865","page","type-page","status-publish","hentry"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/pages\/14865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/users\/624"}],"replies":[{"embeddable":true,"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/comments?post=14865"}],"version-history":[{"count":8,"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/pages\/14865\/revisions"}],"predecessor-version":[{"id":14877,"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/pages\/14865\/revisions\/14877"}],"up":[{"embeddable":true,"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/pages\/8189"}],"wp:attachment":[{"href":"https:\/\/labs.icahn.mssm.edu\/minervalab\/wp-json\/wp\/v2\/media?parent=14865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}