{"id":11891,"date":"2026-11-17T11:00:41","date_gmt":"2026-11-17T02:00:41","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=11891"},"modified":"2026-11-17T11:09:52","modified_gmt":"2026-11-17T02:09:52","slug":"nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-nemotron-3-5-super-vl-120b-a12b-bf16\/","title":{"rendered":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16: 80GB+ VRAM, GGUF Builds"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16\">nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-nvidia-nvidia-nemotron-3-5-super-vl-en\/\">NVIDIA-Nemotron-3.5-Super-VL guide (2 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Publisher guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-nvidia-en\/\">NVIDIA: models and licenses<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-13<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>openmdw-1.1<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-safetensors-en\/\">safetensors<\/a><\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>NVIDIA Corporation has released &#8220;NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16&#8221;, the full-precision version of its vision-language model supporting inference, coding, tool use, document understanding, and video comprehension. This BF16 model is provided for developers aiming for customization, domain adaptation, and full-precision evaluation. According to the model card, it adopts a hybrid architecture combining Mamba-2, Mixture-of-Experts (MoE), and attention layers with the C-RADIO vision encoder and a vision-language connector.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Architecture: Mamba-2\u2013Transformer hybrid Mixture of Experts (MoE) with Multi-Token Prediction (MTP)<\/li>\n<li>Parameters: 120B total \/ 12B active<\/li>\n<li>Context Length: Up to 1M tokens<\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>Benchmark comparison tables from the model card (including other open-weight models) are as follows:<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Benchmark<\/th>\n<th style=\"text-align: right;\">Nemotron 3.5 SuperGA BF16<\/th>\n<th style=\"text-align: right;\">Qwen3.5-122B-A10B<\/th>\n<th style=\"text-align: right;\">Qwen3.8-Flash-Next<\/th>\n<th style=\"text-align: right;\">DeepSeek-V4-Flash0731<\/th>\n<th style=\"text-align: right;\">Nemotron 3 Ultra<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>GPQA-Diamond<\/td>\n<td style=\"text-align: right;\">89.52<\/td>\n<td style=\"text-align: right;\">86.7<\/td>\n<td style=\"text-align: right;\">92.7<\/td>\n<td style=\"text-align: right;\">89.6<\/td>\n<td style=\"text-align: right;\">87.0<\/td>\n<\/tr>\n<tr>\n<td>HLE, text-only<\/td>\n<td style=\"text-align: right;\">31.79<\/td>\n<td style=\"text-align: right;\">24.2<\/td>\n<td style=\"text-align: right;\">39.6<\/td>\n<td style=\"text-align: right;\">35.8<\/td>\n<td style=\"text-align: right;\">29.2<\/td>\n<\/tr>\n<tr>\n<td>MMLU-ProX<\/td>\n<td style=\"text-align: right;\">76.91<\/td>\n<td style=\"text-align: right;\">83.2<\/td>\n<td style=\"text-align: right;\">83.0<\/td>\n<td style=\"text-align: right;\">85.5<\/td>\n<td style=\"text-align: right;\">83.1<\/td>\n<\/tr>\n<tr>\n<td>LiveCodeBench v6<\/td>\n<td style=\"text-align: right;\">88.22<\/td>\n<td style=\"text-align: right;\">76.7<\/td>\n<td style=\"text-align: right;\">94.1<\/td>\n<td style=\"text-align: right;\">94.6<\/td>\n<td style=\"text-align: right;\">89.2<\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Verified<\/td>\n<td style=\"text-align: right;\">71.10<\/td>\n<td style=\"text-align: right;\">71.9<\/td>\n<td style=\"text-align: right;\">78.7<\/td>\n<td style=\"text-align: right;\">75.4<\/td>\n<td style=\"text-align: right;\">73.9<\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Pro<\/td>\n<td style=\"text-align: right;\">51.78<\/td>\n<td style=\"text-align: right;\">44.9<\/td>\n<td style=\"text-align: right;\">60.37<\/td>\n<td style=\"text-align: right;\">56.91<\/td>\n<td style=\"text-align: right;\">49.66<\/td>\n<\/tr>\n<tr>\n<td>Terminal-Bench 2.1<\/td>\n<td style=\"text-align: right;\">66.70<\/td>\n<td style=\"text-align: right;\">48.70<\/td>\n<td style=\"text-align: right;\">85.80<\/td>\n<td style=\"text-align: right;\">76.80<\/td>\n<td style=\"text-align: right;\">54.80<\/td>\n<\/tr>\n<tr>\n<td>OSWorld-Verified<\/td>\n<td style=\"text-align: right;\">51.14<\/td>\n<td style=\"text-align: right;\">51.5<\/td>\n<td style=\"text-align: right;\">55.8<\/td>\n<td style=\"text-align: right;\">N\/A<\/td>\n<td style=\"text-align: right;\">N\/A<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>According to the evaluation results published by the authors, it scores 89.52 on GPQA-Diamond, which measures difficult scientific questions, outperforming some of the comparison models. It also records high figures on LiveCodeBench v6, which handles new competitive programming problems, and Terminal-Bench 2.1, which evaluates agent-based terminal operation. On the other hand, it falls behind other comparison models in general knowledge metrics such as MMLU-ProX, and does not achieve the highest values in every field.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>The primary feature of this model is its ability to integrate and process three modalities: text, images, and video. In particular, because it supports an extremely long context length of up to 1M (1 million) tokens, it is suited for understanding vast documents spanning thousands of pages, analyzing video content of up to 2 minutes, and performing advanced reasoning while maintaining complex dialogue history.<\/p>\n<p>Specific strengths and expected use cases include:<\/p>\n<ul>\n<li><strong>Multimodal Document and Video Understanding<\/strong>: Equipped with the C-RADIO vision encoder, it excels in OCR capabilities to accurately read text and formulas within images, and the ability to grasp events in videos chronologically. It demonstrates high performance in tasks such as document analysis and video summarization.<\/li>\n<li><strong>Advanced Coding and Agent Tasks<\/strong>: Having undergone mid-training specialized for software engineering, it is oriented toward solving real GitHub issues and acting as an agent that executes commands in a terminal to complete work. High scores on LiveCodeBench and SWE-bench back up its capability.<\/li>\n<li><strong>Native Speculative Decoding<\/strong>: Because it incorporates a Multi-Token Prediction (MTP) head, it can perform speculative decoding with the model alone, without preparing an additional draft model. This is expected to improve inference speed.<\/li>\n<li><strong>Multilingual Support and Customization<\/strong>: It supports multiple major languages including Japanese. Furthermore, since it is released as a BF16 full-precision version, it is optimal as a base model for fine-tuning specialized in specific business domains or creating proprietary quantized models.<\/li>\n<\/ul>\n<p>These capabilities are built upon a massive dataset containing over 20 trillion tokens of foundational training data, more than 10 trillion tokens of text data, 1 million to 1 billion images, and 10,000 to 1 million hours of video. In particular, data in specialized domains such as mathematics, science, law, and finance, as well as high-quality code data, have been learned with emphasis.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 124.5B parameters<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Your VRAM<\/th>\n<th>Quantization<\/th>\n<th>File size<\/th>\n<th>Est. memory needed<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>80GB class (A100 \/ H100)<\/td>\n<td>Q3_K_XL<\/td>\n<td>61.2GB<\/td>\n<td>73.5GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><strong>Inference engine support<\/strong> (architecture name matched against each project&#8217;s own model registry in its source code, checked 2026-11-17): llama.cpp: registered, vLLM: registered, MLX (mlx-lm): not registered. &#8220;Not registered&#8221; means the name is absent from that registry today, not that the model cannot run.<\/p>\n<p><em>Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model&#8217;s authors. File sizes are measured from the converted build <a href=\"https:\/\/huggingface.co\/unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF\">unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF<\/a>. Compare with other models in our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a>. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:hardware --><\/p>\n<p><!-- lmw:runnability --><\/p>\n<h2>Can You Run It Locally?<\/h2>\n<p><strong>Runs in Ollama, LM Studio and llama.cpp via a converted build.<\/strong><\/p>\n<p>The publisher ships safetensors, but <a href=\"https:\/\/huggingface.co\/unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF\">unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF<\/a> provides a GGUF build you can use.<\/p>\n<p><strong>License \u2014 <code>openmdw-1.1<\/code>:<\/strong> A custom license from the publisher. Check the original terms directly, including whether commercial use is permitted.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats, converted builds we have found, and each engine&#8217;s own model registry. &#8220;Not found&#8221; means we have not seen such a build, not that none exists. License summaries are not legal advice \u2014 check the publisher&#8217;s original terms before relying on them.<\/em><\/p>\n<p><!-- \/lmw:runnability --><\/p>\n<p><!-- lmw:lab --><\/p>\n<h2>Our Own Measurements<\/h2>\n<h3>Measurements We Did Not Take<\/h3>\n<p>We have not confirmed that this site meets the commercial-use terms of this model&#8217;s license (<code>openmdw-1.1<\/code>). Because this site carries advertising, we did not run the model (no CPU run, answers, quantization comparison, conversion or generation).<\/p>\n<p><!-- \/lmw:lab --><\/p>\n<p><!-- lmw:peers --><\/p>\n<h2>Recent Models in the Same Size Class<\/h2>\n<p><em>Models with <\/em><em>over 40B<\/em><em> parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site&#8217;s estimates; licenses are as stated on the model cards.<\/em><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Parameters<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>deepseek-ai\/DeepSeek-V4.1-Flash-1017<\/td>\n<td>763.2B<\/td>\n<td>\u2014<\/td>\n<td>mit<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/deepseek-v4-1-flash-1017-released\/\">DeepSeek-V4.1-Flash-1017 Vision-Language Model: ~570GB Memory<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>Qwen\/Qwen3.8-Flash-Next<\/td>\n<td>180.0B<\/td>\n<td>\u2014<\/td>\n<td>qwen-community-1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/05\/qwen-3-8-flash-next-released\/\">Qwen3.8-Flash-Next Multimodal MoE Model: ~402GB Memory<\/a> (2026-10-04)<\/td>\n<\/tr>\n<tr>\n<td>ggml-org\/GLM-5.3-Flash-GGUF<\/td>\n<td>321.3B<\/td>\n<td>\u2014<\/td>\n<td>other<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/04\/glm-5-3-flash-gguf-released\/\">GLM-5.3-Flash-GGUF Vision-Language Model: ~150GB Memory<\/a> (2026-10-03)<\/td>\n<\/tr>\n<tr>\n<td>bartowski\/Intern-S2-397B-GGUF<\/td>\n<td>403.4B<\/td>\n<td>\u2014<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/15\/intern-s2-397b-gguf-released\/\">Intern-S2-397B-GGUF Vision-Language Model: ~102GB Memory<\/a> (2026-09-15)<\/td>\n<\/tr>\n<tr>\n<td>deepseek-ai\/DeepSeek-V4.1-Flash<\/td>\n<td>763.2B<\/td>\n<td>\u2014<\/td>\n<td>mit<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/10\/deepseek-v4-1-flash-released\/\">DeepSeek-V4.1-Flash 552B Multimodal MoE Model: ~570GB Memory<\/a> (2026-09-10)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:peers --><\/p>\n<h2>How to Get It<\/h2>\n<p>This model is available in safetensors format from the Hugging Face repository. The &#8220;OpenMDW-1.1&#8221; license applies, allowing use for both commercial and non-commercial purposes. At this time, gated settings requiring individual license agreement upon acquisition are not applied.<\/p>\n<p>Recommended execution environments include vLLM (nightly version or v0.32.0 and later) and SGLang (v0.5.20 and later). Operation in BF16 full precision requires high computational resources, and the official documentation exemplifies configurations using 4 H100 GPUs or 2 GB200 GPUs.<\/p>\n<p>A command example for starting a server using vLLM and accepting image and video inputs is as follows:<\/p>\n<pre><code class=\"language-bash\">export MODEL=nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16\n\nvllm serve $MODEL \\\n  --served-model-name nemotron-3.5-super-vl \\\n  --tensor-parallel-size 4 \\\n  --trust-remote-code \\\n  --gpu-memory-utilization=0.85 \\\n  --allowed-local-media-path=\/ \\\n  --max-num-seqs=32 \\\n  --limit-mm-per-prompt '{&quot;video&quot;: 1, &quot;image&quot;: 1}' \\\n  --video-pruning-rate 0.5 \\\n  --media-io-kwargs '{&quot;video&quot;: {&quot;fps&quot;: 2, &quot;num_frames&quot;: 256}}' \\\n  --enable-auto-tool-choice \\\n  --tool-call-parser qwen3_coder \\\n  --reasoning-parser nemotron_v3 \\\n  --speculative_config.method mtp \\\n  --speculative_config.num_speculative_tokens 3\n<\/code><\/pre>\n<p>As recommended parameters during inference, temperature 1.0 and top_p 0.95 are suggested for text generation, while temperature 0.6 and top_p 0.95 are suggested for visual tasks. Additionally, by controlling the <code>enable_thinking<\/code> argument of the chat template, you can toggle the reasoning (thinking) mode on and off.<\/p>\n<p><!-- lmw:variants --><\/p>\n<h2>Quantized and Converted Variants<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Added<\/th>\n<th>Publisher<\/th>\n<th>Format<\/th>\n<th>Repository<\/th>\n<th>Smallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-10-16<\/td>\n<td>unsloth<\/td>\n<td>GGUF<\/td>\n<td><a href=\"https:\/\/huggingface.co\/unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF\">unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF<\/a><\/td>\n<td>Q3_K_XL 73.5GB (fits in 80GB VRAM)<\/td>\n<\/tr>\n<tr>\n<td>2026-11-17<\/td>\n<td>nvidia<\/td>\n<td>NVFP4<\/td>\n<td><a href=\"https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4\">nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4<\/a><\/td>\n<td>NVFP4 83.8GB (does not fit a single consumer GPU)<\/td>\n<\/tr>\n<tr>\n<td>2026-11-17<\/td>\n<td>nvidia<\/td>\n<td>NVFP4<\/td>\n<td><a href=\"https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-LiLiCorr\">nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-LiLiCorr<\/a><\/td>\n<td>NVFP4 1.5GB (fits in 4GB VRAM)<\/td>\n<\/tr>\n<tr>\n<td>2026-11-17<\/td>\n<td>DevQuasar<\/td>\n<td>GGUF<\/td>\n<td><a href=\"https:\/\/huggingface.co\/DevQuasar\/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF\">DevQuasar\/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF<\/a><\/td>\n<td>Q3_K_M 75.1GB (fits in 80GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>File sizes of each build:<\/p>\n<ul>\n<li>Available builds in unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF: IQ1_M 43.0GB \/ IQ2_XXS 47.6GB \/ IQ2_M 52.0GB \/ Q2_K_XL 53.8GB \/ IQ3_XXS 55.7GB \/ Q3_K_XL 61.2GB \/ Q4_K_XL 80.9GB \/ Q5_K_XL 103.1GB \/ Q6_K_XL 112.7GB \/ Q8_0 122.6GB<\/li>\n<li>Available builds in nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4: NVFP4 69.9GB<\/li>\n<li>Available builds in nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-LiLiCorr: NVFP4 1.2GB<\/li>\n<li>Available builds in DevQuasar\/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF: Q2_K 49.8GB \/ Q3_K_M 62.6GB \/ Q4_K_M 80.1GB \/ Q5_K_M 89.1GB \/ Q6_K 105.2GB \/ Q8_0 119.6GB<\/li>\n<\/ul>\n<p>In addition, 32 converted build(s) from other uploaders exist on Hugging Face; this site lists only builds from the model&#8217;s publisher or established quantization maintainers.<\/p>\n<p><em>This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:variants --><\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-nemotron-3-5-super-vl-120b-nvfp4-2\/\">NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4: ~84GB Memory<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-dory-1-0-4b-recurrent-llm\/\">NVIDIA Releases Dory1.0-4B: A Recurrent 4B LLM with Dynamic Loops<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-muse-spark-open-816b-a42b-dflash2-2\/\">Muse-Spark-Open-816B-A42B-DFlash2 Vision-Language Model: 12GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/10\/nvidia-releases-deepseek-v4-pro-nvfp4\/\">DeepSeek-V4-Pro-0813-nvfp4-DSpark: ~1005GB Memory<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Find models by VRAM<\/strong> (This model needs at least 80GB) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a><\/li>\n<li><strong>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-nvidia-nvidia-nemotron-3-5-super-vl-en\/\">NVIDIA-Nemotron-3.5-Super-VL family overview (2 articles, 4 converted builds)<\/a><\/li>\n<li><strong>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-llama-cpp-en\/\">llama.cpp<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-vllm-en\/\">vLLM<\/a><\/li>\n<li><strong>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-fp4-en\/\">NVFP4 \/ MXFP4 format guide and models<\/a><\/li>\n<li><strong>Learn about the publisher<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-nvidia-en\/\">NVIDIA: models, licenses and articles<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16\">https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16<\/a><\/li>\n<li><a href=\"https:\/\/research.nvidia.com\/labs\/nemotron\/files\/https:\/\/research.nvidia.com\/labs\/nemotron\/files\/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf\">https:\/\/research.nvidia.com\/labs\/nemotron\/files\/https:\/\/research.nvidia.com\/labs\/nemotron\/files\/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf<\/a><\/li>\n<li><a href=\"https:\/\/assets.ngc.nvidia.com\/products\/api-catalog\/nemotron-3.5-super-vl\/Nemotron_3.5_Super_VL_EU_Training_Content_Summary.pdf\">https:\/\/assets.ngc.nvidia.com\/products\/api-catalog\/nemotron-3.5-super-vl\/Nemotron_3.5_Super_VL_EU_Training_Content_Summary.pdf<\/a><\/li>\n<\/ul>\n<p><!-- lmw:updates --><\/p>\n<h2>Update History<\/h2>\n<ul>\n<li>2026-11-17: Added converted builds to \u201cQuantized and Converted Variants\u201d: nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4, nvidia\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-LiLiCorr, DevQuasar\/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF<\/li>\n<li>2026-11-17: Updated the hardware requirements table with the actual file sizes of unsloth\/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF.<\/li>\n<li>2026-11-17: Changed the title to show what the article covers (VRAM requirements, file list, etc.).<\/li>\n<\/ul>\n<p><!-- \/lmw:updates --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Explore NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16, a full-precision vision-language model with a hybrid architecture and 1M context length.<\/p>\n","protected":false},"author":1,"featured_media":16744,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[165,695,3470,3479,1547,592,1952,3481],"class_list":["post-11891","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-moe-en","tag-nvidia-en","tag-nvidia-nemotron-3-5-super-vl-en","tag-nvidia-nemotron-3-5-super-vl-120b-a12b-bf16-en","tag-verified","tag-vllm-en","tag-vlm-en","tag--en"],"lang":"en","translations":{"en":11891,"ja":11889},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11891","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=11891"}],"version-history":[{"count":5,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11891\/revisions"}],"predecessor-version":[{"id":17807,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11891\/revisions\/17807"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/16744"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=11891"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=11891"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=11891"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}