NVIDIA
Operating mode
Use this to bias workload recommendations toward responsiveness, background autonomy, lighter serving, or multi-GPU scale-out.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
The RTX 5090 Laptop is NVIDIA's Blackwell mobile flagship, featuring 24 GB of GDDR7 at 896 GB/s bandwidth in a 95–150W TGP package. Based on the GB203 die (not the desktop RTX 5090's GB202), it delivers 52 TFLOPS FP16 and 1,824 AI TOPS — making it the first laptop GPU with enough VRAM to run 70B models at Q3/Q4 without CPU offloading. Available from March 2025, it represents a major step forward for portable AI inference compared to the 16 GB Ada laptop generation.
Beyond LLMs
What AI tasks this GPU can handle — from text generation to image and video creation.
| Capability | Status | Representative Model |
|---|---|---|
| LLM Chat (7B) | Runs natively | Llama 3.1 8B Q4 |
| LLM Coding (30B) | Runs natively | Qwen 3 30B Q4 |
| LLM Large (70B) | Won’t fit | Llama 3.1 70B Q4 |
| Image Gen (SDXL) | Runs natively | SDXL 1.0 FP16 |
| Image Gen (Flux) | Runs with offload | Flux.1 Dev FP16 |
| Image Gen (SD 3.5) | Runs natively | SD 3.5 Large FP16 |
| Video Short (25f) | Runs natively | LTX Video 2B |
| Video Long (100f) | Won't fit | Wan Video 14B |
Architecture
Blackwell is NVIDIA's fifth-generation RTX architecture, built on TSMC's 4NP process. It introduces 5th-generation Tensor Cores with native FP4 precision support, enabling double the inference throughput per watt compared to Ada Lovelace's FP8 operations. Key innovations include the Neural Rendering Pipeline for AI-driven shading and the debut of GDDR7 memory in consumer GPUs.
AI Relevance
FP4 Tensor Cores deliver the highest tokens-per-watt efficiency in any consumer architecture. Native FP4 quantization means models can run at lower precision with minimal quality loss, effectively doubling the effective VRAM for model weights.
購入アドバイス
ローカルAIに最適な選択
上位50モデル中26モデルを快適に実行 — ローカル推論の万能選手です。
24.0 GB
VRAM
このGPUに最適なモデル
What will limit you first
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Best upgrade itinerary
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Unlocks 1 additional models that do not fit on the current setup.
もっと余裕が欲しいですか？ MacBook Pro M4 Max 36GB (36.0 GB unified memory) が次のステップアップです。
Chat
SThis model is a direct match for chat. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Coding
SThis model is a direct match for coding. It belongs to a current frontier family for local AI. It should run, but memory headroom will be limited. Known channels: huggingface, ollama, lm-studio.
Agentic Coding
SThis model is still usable for agentic-coding, but it is not the most specialized pick. It belongs to a current frontier family for local AI. It should run, but memory headroom will be limited. Known channels: huggingface, lm-studio.
Reasoning
SThis model is a direct match for reasoning. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
RAG
AThis model is a direct match for rag. It sits in the middle of the current model mix. It fits natively with comfortable headroom. Known channels: huggingface, ollama.
Qwen3-Coder 30B A3B InstructQwen3-VL 30B A3B Instruct
GPT-OSS 20BQwen 3 14B
Phi-4-reasoning-plus 14BQwen 3.5 27BQwen 3 30B A3B
Magistral Small 2507Devstral Small 2 24B InstructQwen 3.5 9BQwen 3.6 27BDevstral Small 1.1Nemotron Cascade 2 30B A3BQwen 3 8BNemotron 3 Nano 30BMinistral 3 14B
Gemma 4 26B A4BQwen 3.5 4BNemotron Nano 8BQwen 3.5 35B A3BPhi-4 Mini Reasoning 4BQwen 3 32BQwen 3.6 35B A3B
Jina Embeddings v3
BGE M3
EXAONE 4.0 32BQwen 3.5 397B A17BDevstral 2 123B Instruct
Kimi K2.5Kimi K2.6
DeepSeek V4 ProQwen 3.5 122B A10BDeepSeek V4 FlashMistral Small 4 119B
Command A 111BQwen 2.5 VL 72BGPT-OSS 120BQwen3-Coder-Next
GLM-5.1Pixtral Large 124BGLM-5DeepSeek V3.2Qwen 3 235B A22BQwen3-Coder 480B A35B InstructGemma 4 31BLeanstral 119B A6BDeepSeek Coder V2 236BDeepSeek R1 671BDeepSeek V3.1 671Bもう少しで届く
もう少しメモリがあれば動く高品質モデル
Image & Video Generation
41 of 52 models can generate images or video on your RTX 5090 Laptop 24GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | 700ms | S |
| Stable Diffusion 1.5Image | 512×768 | ~1.4s | S |
| Realistic Vision v5.1Image | 512×768 | ~1.4s | S |
| DreamShaper 8Image | 512×768 | ~1.4s | S |
| LCM DreamShaper v7Image | 512×768 | 400ms | S |
| PixArt-SigmaImage | 1024×1024 | ~5.7s | S |
| FramePack I2VVideo | 256×256 | ~10.5s/frame | S |
| SDXL TurboImage | 512×512 | 700ms | S |
| SDXL LightningImage | 1024×1024 | ~2.1s | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~5.7s | S |
| Playground v2.5Image | 1024×1024 | ~8.6s | S |
| RealVisXL v5.0Image | 1024×1024 | ~6.4s | S |
| DreamShaper XLImage | 1024×1024 | ~6.4s | S |
| Juggernaut XL v9Image | 1024×1024 | ~6.4s | S |
| Animagine XL 3.1Image | 1024×1024 | ~6.4s | S |
| Pony Diffusion V6 XLImage | 1024×1024 | ~6.4s | S |
| Animagine XL 4.0Image | 1024×1024 | ~6.4s | S |
| Illustrious XLImage | 1024×1024 | ~6.4s | S |
| Wan Video 2.1 1.3BVideo | 256×256 | ~4.2s/frame | S |
| Stable Diffusion 3.5 MediumImage | 1024×1024 | ~10s | S |
| Flux.2 Klein 4BImage | 1024×1024 | ~1.7s | S |
| LTX Video 2BVideo | 768×512 | ~5s/frame | S |
| KolorsImage | 1024×1024 | ~11.4s | S |
| Stable CascadeImage | 1024×1024 | ~14.3s | S |
| AuraFlow v0.3Image | 1536×1536 | ~25.7s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~31.4s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | ~5.7s | S |
| CogVideoX 2BVideo | 720×480 | ~5s/frame | A |
| HunyuanVideoVideo | 256×256 | ~10.5s/frame | A |
| ChromaImage | 256×256 | ~10.5s | A |
| Z-Image TurboImage | 1536×1536 | ~5.9s | B |
| Flux.1 DevImage | 256×256 | ~25.7s | B |
| Flux.1 SchnellImage | 256×256 | ~5s | B |
| LTX Video 13BVideo | 256×256 | ~10.5s/frame | B |
| Flux.1 Kontext DevImage | 256×256 | ~28.5s | B |
| AnimateDiff v1.5.3Video | 512×768 | ~2.6s/frame | B |
| Cosmos Diffusion 7BVideo | 256×256 | ~15.8s/frame | B |
| CogVideoX 5BVideo | 256×256 | ~15s/frame | B |
| Wan2.2 TI2V 5BVideo | 256×256 | ~15s/frame | B |
| Flux.2 Klein 9BImage | 256×256 | ~5.2s | D |
| Flux.1 Fill DevImage | 256×256 | ~24.3s | D |
| Mochi 1 PreviewVideo | 256×256 | ~9.4s/frame | F |
| HunyuanVideo 1.5Video | 256×256 | ~8.8s/frame | F |
| Helios 14BVideo | 256×256 | ~10.8s/frame | F |
| SkyReels V2 14BVideo | 256×256 | ~10.8s/frame | F |
| Wan Video 2.1 14BVideo | 256×256 | ~10.8s/frame | F |
| Wan Video 2.2 14BVideo | 256×256 | ~10.8s/frame | F |
| Qwen ImageImage | 256×256 | ~9.6s | F |
| Qwen Image EditImage | 256×256 | ~9.6s | F |
| Flux.2 DevImage | 256×256 | ~4m 30s | F |
| MAGI-1Video | 256×256 | ~13.4s/frame | F |
| HunyuanImage 3.0Image | 256×256 | ~16.9s | F |
Image models estimated at 1024×1024 (28 steps, FP16). Video models estimated at 768×512 (25 frames, 30 steps, FP16). Actual performance varies with runtime and system load.
Upgrade paths
See what you unlock with more powerful hardware
アップグレードオプション
Unlocks 1 additional models that do not fit on the current setup.
〜$2,499 MSRP
RTX 5000 Ada 32GBNVIDIAアップグレードUnlocks 6 additional models that do not fit on the current setup.
〜$4,000 MSRP
Unlocks 17 additional models that do not fit on the current setup.
〜$1,099 MSRP
Unlocks 45 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 109%.
〜$8,000 MSRP
RTX 5090 Laptop 24GB (24 GB VRAM) can run these top models: Qwen3-Coder 30B A3B Instruct (score: 97/100), Qwen3-VL 30B A3B Instruct (score: 96/100), GPT-OSS 20B (score: 95/100). See the full compatibility list above.
RTX 5090 Laptop 24GB has 24 GB of VRAM available for AI model inference. This determines which models and quantization levels you can run locally.
Yes, RTX 5090 Laptop 24GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on RTX 5090 Laptop 24GB, we recommend Devstral Small 2 24B Instruct. It achieves 55.3 tokens per second with 40K context window. This model is a direct match for coding. It belongs to a current frontier family for local AI. It should run, but memory headroom will be limited. Known channels: huggingface, ollama, lm-studio.
There are 4 upgrade path(s) from RTX 5090 Laptop 24GB: MacBook Pro M4 Max 36GB, RTX 5000 Ada 32GB. Upgrading would unlock larger models and faster inference speeds.
Yes, RTX 5090 Laptop 24GB with 24 GB of usable memory can run Flux.1 Dev at FP16 natively. Flux is a 12B parameter diffusion transformer that produces high-quality images. You can also run the Schnell variant for faster generation.
RTX 5090 Laptop 24GB (24 GB VRAM) can handle various AI generation tasks beyond LLMs. For image generation, SDXL and Stable Diffusion 3.5 run well. Flux.1 Dev also runs natively for state-of-the-art image quality. For video, LTX Video 2.3 can generate short clips. Check the AI Capability Matrix above for detailed compatibility.
RTX 5090 Laptop 24GB is excellent for AI image generation. With 24 GB of usable memory, it runs all major diffusion models including Flux.1, SDXL, and Stable Diffusion 3.5 at full precision. You can generate high-resolution images quickly and even handle video generation models.
Yes, RTX 5090 Laptop 24GB with 24 GB of usable memory can run Qwen 3.5 27B at Q4_K_M (~16.5 GB) with ~7 GB headroom for context and runtime. Quality at Q4 is very close to full precision for most tasks. Run it with: ollama run qwen3.5:27b
With 24 GB on RTX 5090 Laptop 24GB, Q4_K_M is the sweet spot for 27B-35B models, Q6_K for 14B models, and Q8_0 for 8B-9B models. The general rule: use the highest quantization that fits with at least 2-3 GB headroom for KV cache and runtime.
RTX 5090 Laptop 24GB has enough memory for many local LLMs, but bandwidth still matters a lot for real speed. Once a model fits, a faster-memory GPU can feel significantly better than a slower setup with similar capacity.
Compare with similar
