What Can the NVIDIA GeForce RTX 4090 Run?

The sweet spot for local reasoning. Competitive with o1-mini on math and coding tasks at 32B scale.

Alibaba's advanced reasoning model. Extended thinking and reflection enables GPT-o1-level problem solving.

Near-frontier performance from a local 32B model. Exceptional multilingual reasoning and instruction following.

The best open-weight code model available. Matches GPT-4o on coding benchmarks, runs locally at 20GB VRAM.

An open-weight reasoning model capable of long chains of thought before answering.

The most transparent large language model ever released — weights, training data, code, evaluation harnesses, and training logs all fully public. Essential for research reproducibility and academic citation.

Native support for 23 languages. The single best open multilingual foundation model available for researchers building localized or translation-heavy pipelines.

HumanEval 92% — the best single-GPU coding model for RTX 5090 owners. Excels at multi-file edits, refactoring, and agentic tool use pipelines. The definitive open coding model at the 20GB VRAM tier.

Google's largest open Gemma model. Competes with 70B-class models from previous generations.

Community top pick for a single 24GB GPU. Supports 201 languages natively with vision-language capability built in. IFBench 76.5 and AIME 91.3 — outperforms GPT-5.2 on instruction following.

Outstanding performance at the 24GB VRAM tier with a native Google vision-language encoder integrated directly into the weights. MMLU-Pro score of 67.5.

6-second 720P clips on a single 16GB GPU — the easiest entry point into local video generation. Apache 2.0 commercial license with active ComfyUI integration. Best for social media automation and rapid prototyping.

Full open-source Sora replication — weights, training code, and full data pipeline are all public. The most transparent video generation model. Essential for researchers studying text-to-video architectures and training dynamics.

A large hybrid model family designed specifically for efficient on-device deployment.

A general-purpose reasoning and chat model trained from scratch by NVIDIA, featuring a low-latency MoE architecture.

Mistral's dedicated code model. Industry-leading performance on FIM (fill-in-middle) and complex code generation.

Highly capable 22B model from Mistral AI. Excellent instruction following for enterprise chat applications.

A medium-sized Mixture-of-Experts foundation model from Baidu.

Cinematic-quality video generation accessible at just 14GB VRAM with model offloading. The most democratized cinematic video tool available. Produces Hollywood-grade motion blur, depth of field, and lighting consistency.

4-step generation with Apache 2.0 commercial license. The fastest high-quality local image model — produces studio-grade output in under 3 seconds on a 24GB GPU. The go-to for commercial product photography pipelines.

Best text-in-image rendering and the largest open LoRA fine-tune ecosystem with 50,000+ community models. The creative industry's preferred foundation for style transfer, brand consistency, and character sheet generation.

Meta's flagship 4B music model with melody conditioning from reference audio clips. Best for cinematic scoring and mood-driven generation. CC-BY-NC-4.0. Industry standard for AI-assisted film and game soundtrack production.

OpenAI's open-weight LLM, supporting configurable reasoning efforts (low, medium, high).

An advanced reasoning model with flexible 'thinking budget' control and self-reflection capabilities.

Specialized code completion model trained on 600+ programming languages. Top-tier for in-IDE completions.

Second-generation Devstral for agentic coding, built for tool use, multi-file editing, and software engineering agents with vision support.

A vision-language model featuring upgrades to visual perception, spatial reasoning, and image understanding.

Qwen-2.5 distilled reasoning model. Strong chain-of-thought and math at an accessible VRAM cost.

Exceptional 14B all-rounder. Competitive with many 30B+ models on reasoning and coding benchmarks.

Top-tier code model for 12GB+ GPUs. Strong at agentic coding, multi-file edits, and complex refactors.

Microsoft's flagship small model. Trained on synthetic data with exceptional reasoning and STEM performance.

Integrates breakthroughs in multimodal learning, architectural efficiency, and reinforcement learning scale.

A lightweight open model focused on high-quality, reasoning-dense synthetic data.

State-of-the-art open-weight vision model. Analyze charts, read documents, describe complex scenes.

128K context window in a 12B model. Joint Mistral AI & NVIDIA collaboration — excellent for long-document tasks.

Google's mid-tier Gemma 3. Multimodal capable, 128K context, strong multilingual reasoning.

50-step SDXL quality in just 4 steps via adversarial diffusion distillation. Fully Apache 2.0 commercial. ComfyUI-native workflow. The fastest path from creative brief to production asset on 8GB VRAM hardware.

Matches or beats ElevenLabs Flash on prosody naturalness. 3-second voice cloning from a reference clip with no fine-tuning required. The top locally-run TTS for podcast production, audiobooks, and voice-over automation.

Best local music model for 2026. Generates up to 10 minutes of audio with precise genre, instrument, tempo, and lyrics control. Apache 2.0 commercial license. The definitive tool for indie game composers and content creators.

A 9B vision-language model optimized for local deployment and low-latency applications.

Open source coding models specializing in coding and tool calling, based on a new base model.

A lightweight, open model built as a foundation for creating specialized function calling models.

A family of open language models designed to enable scientific research into language modeling.

A coding model from Mistral AI designed for codebase exploration and engineering agents.

Tiny model with 4K native output capability — best image-per-VRAM-dollar ratio available. Apache 2.0. Runs on GTX 1070 8GB. The only model sub-1GB that produces print-resolution imagery with coherent composition.

Photorealistic lip sync at 30+ FPS in real time. The best model for live avatar streaming and talking-head video creation. MIT license with active Discord community. Integrates natively with OBS and streaming tools.

One photo → talking head video with natural head movement, blinks, and mouth articulation. MIT license. No video sample required — just a single still image and an audio clip. The most accessible local avatar creation tool.

The classic vision-language model. Describe images, answer visual questions locally. Proven and reliable.

A family of open-weight, dense models trained from scratch by Essential AI.

A highly cost-effective, high-performing 8B instruction tuned model.

A specialized Vision Language Model (VLM) for optical character recognition tasks.

Open safety models built on the gpt-oss foundation to help classify and filter text content.

Lightweight open models supporting multilingual tasks, RAG, coding, and tool use.

Video + multi-image + text understanding at 8B parameters. The best vision model for 8GB VRAM setups — handles 40-frame video clips, multi-image comparison, and document understanding in a single context window.

Google's code-tuned Gemma variant. Excellent at code completion tasks inside IDEs.

Meta's powerhouse 8B model with 128K context. Excellent all-rounder for chat, code, and reasoning.

Llama-3 distilled reasoning model. Outperforms GPT-4o on several math benchmarks at 8B scale.

The 'OLMo of coding' — fully transparent training pipeline with HumanEval 83.5%. Every component is open: weights, data, and methodology. The most trustworthy small coding model for compliance-sensitive teams.

Math Index 91.0 — the highest math score at the 8GB VRAM tier. NVIDIA's distilled Llama-3.1 with proprietary reward model training. Ideal for STEM tutoring and quantitative analysis on a single mid-range GPU.

Top-ranked self-hosted embedding on MTEB English — outperforms all sub-72B models. 32K context window for ultra-long document encoding. The upgrade path from BGE-M3 for teams needing maximum retrieval precision.

The model that proved smaller can beat bigger. Mistral 7B outperforms many 13B models with blazing fast speed.

Distilled reasoning power in a 7B package. Excels at math, logic, and step-by-step problem solving.

Highly competitive 7B model with long context and strong multilingual support. A top value pick.

Best-in-class 7B code model. Excellent at multi-language completion, bug fixing, and code explanation.

HumanEval 76.8% at just 6.7B — beats models 10× its size through OSS-Instruct training on real open-source code. The best option for code completion on 6GB VRAM with quality that defies the parameter count.

The de facto standard for local speech-to-text. Word-level timestamps, speaker diarization, and 99 language support. Essential for transcription pipelines, meeting summarization, and building voice-first AI interfaces.

Click anywhere on an image or video → instant object segmentation. Apache 2.0. Universal segmentation model used in medical imaging, autonomous driving datasets, and content creation. Zero training required for any object class.

Single image → metrically accurate 3D depth map in under 0.3 seconds. Free for research use. Powers 3D scene reconstruction, bokeh simulation, and AR/VR depth estimation pipelines without any calibration data.

Google's strong 4B model with multimodal capability and 128K context. One of the best small models.

Microsoft's multilingual tiny model with enormous 128K context window. Exceptional for document tasks.

Microsoft's best edge release. Fits 8GB RAM and runs fast on M1 MacBook Air in airplane mode. Exceptional at structured reasoning for its size — the top choice for on-device personal assistants and document Q&A.

Compact code-specialized model. Strong at code completion and debugging on very limited hardware.

A generative AI model optimized for use in everyday devices like laptops and phones.

Best-in-class 3B model with 128K context. Outperforms many 7B models on common benchmarks.

Compact and fast. Excellent multilingual and instruction-following performance at tiny VRAM cost.

Flow-matching TTS with no duration modeling — produces the most natural prosody and sentence rhythm of any local voice model. MIT license. The preferred choice for giving local AI agents a human-sounding voice interface.

Encodes PDF pages as images — bypasses all broken PDF parsers for perfect scanned document retrieval. Apache 2.0. The breakthrough for RAG on government forms, research papers, and historical archives with graphical content.

Tiny but capable vision language model. Describe images, read text, answer visual questions locally.

Runs on iPhone in airplane mode. First sub-3B model with native multimodal support — a landmark for on-device AI. Perfect for privacy-preserving mobile apps that need real conversational capability without a server.

Smallest reasoning model you can run locally. Surprising chain-of-thought performance for its size.

Excellent multilingual capabilities for its size. Particularly strong in Chinese and coding tasks.

Runs in-browser via WebGPU — no installation required. Best for Electron apps and Raspberry Pi deployments. HuggingFace's most downloaded edge model with an Apache 2.0 license and full community model ecosystem.

Compact Llama 3.2 with impressively long 128K context window. Perfect for edge deployment.

Google's smallest Gemma 3. Runs on virtually any GPU or even CPU — great for on-device applications.

State-of-the-art embedding model for retrieval tasks. Ranks #1 on multiple MTEB categories.

Captioning, object detection, grounding, OCR, and segmentation in one 770M model — MIT license. The Swiss Army knife of computer vision. Runs on almost any GPU and powers automated image tagging pipelines at scale.

The default local RAG embedding model for 2026. 100 languages, 8K context, and three retrieval modes (dense, sparse, multi-vector) in one model. MIT license. Used in production by thousands of enterprise RAG pipelines.

Smallest Qwen 2.5 — blazing fast on any hardware. Surprisingly capable for its size on simple tasks.

High-quality embedding model with 8K context. Outperforms OpenAI text-embedding-ada-002 on MTEB benchmark.

Non-Transformer architecture with linear context scaling — never degrades on long sequences. Achieves 40,400 tokens/sec on Apple Silicon. The fastest local model for structured extraction pipelines and IoT edge nodes.

Ultra-compact sentence embedding model. Perfect for semantic search and RAG pipelines on any hardware.

CPU-only TTS that runs on Raspberry Pi. The best quality-per-watt ratio of any voice model — 82M parameters producing studio-quality speech synthesis. Apache 2.0 commercial license with no GPU requirement whatsoever.