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.
NVIDIA DGX Spark 128GB is a compact Grace Blackwell personal AI system with 128 GB of coherent unified memory and the NVIDIA CUDA software stack preinstalled. It is aimed at developers who want to prototype, fine-tune, and run much larger local models than fit on 24 GB or 48 GB consumer GPUs, but without jumping straight to a rack-scale server.
Official product page ↗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) | Runs natively | Llama 3.1 70B Q4 |
| Image Gen (SDXL) | Runs natively | SDXL 1.0 FP16 |
| Image Gen (Flux) | Runs natively | 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) | Runs natively | Wan Video 14B |
Consejo de compra
Excelente opción para IA local
Ejecuta 35 de 50 modelos principales bien — un todoterreno sólido para inferencia local.
128.0 GB
Unified memory
Mejores modelos para esta GPU
What will limit you first
El modelo cabe en memoria compartida, pero ahora el verdadero límite es el ancho de banda de esa memoria.
Que quepa no significa velocidad de VRAM dedicada
La memoria unificada o compartida puede hacer que el modelo quepa, pero los tok/s sostenidos pueden quedar muy por debajo de una GPU discreta con memoria dedicada de alto ancho de banda.
La memoria compartida sigue teniendo contención
El sistema operativo, el navegador y el runtime de inferencia compiten por el mismo pool físico de memoria, así que el margen real es menos generoso de lo que sugiere la capacidad bruta.
Best upgrade itinerary
Prioriza ancho de banda, no solo capacidad
Si este workload se siente lento, la siguiente mejora útil suele ser una GPU con mucha más velocidad de memoria, no solo un pequeño aumento de capacidad.
Desbloquea 2 modelos adicionales que hoy no caben en tu setup.
¿Quieres más margen? NVIDIA H200 141GB (141.0 GB VRAM) es el siguiente paso.
Chat
FKimi K2.5 matches Chat and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It is likely to require compromise or offload. Context is capped below the requested workload target (4096 vs 8000). Known distribution channels: huggingface, ollama-cloud.
Coding
FQwen3-Coder-Next is a specialized fit for Coding. It is a recent-generation family, which helps on current local SOTA workloads. It is likely to require compromise or offload. Context is capped below the requested workload target (4096 vs 16000). Known distribution channels: huggingface, ollama, lm-studio.
Agentic Coding
FQwen3-Coder-Next is a specialized fit for Agentic Coding. It is a recent-generation family, which helps on current local SOTA workloads. It is likely to require compromise or offload. Context is capped below the requested workload target (4096 vs 32000). Known distribution channels: huggingface, ollama, lm-studio.
Reasoning
FQwen3-Coder 30B A3B Instruct matches Reasoning and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It is likely to require compromise or offload. Context is capped below the requested workload target (4096 vs 16000). Known distribution channels: huggingface, ollama, lm-studio.
RAG
FQwen 3.5 122B A10B matches RAG and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It is likely to require compromise or offload. Context is capped below the requested workload target (4096 vs 32000). Known distribution channels: huggingface, lm-studio.
Qwen 3.5 122B A10BQwen3-Coder-NextQwen3-Coder 30B A3B InstructQwen 3.6 35B A3BQwen3-VL 30B A3B Instruct
Command A 111B
Mistral Small 4 119BQwen 3.5 35B A3BDevstral 2 123B InstructQwen 2.5 VL 72BQwen 3 30B A3BQwen 3.5 9BQwen 3.5 27BQwen 3.5 4B
GPT-OSS 120BMagistral Small 2507Qwen 3 8BQwen 3 32BQwen 3.6 27BDevstral Small 2 24B InstructGPT-OSS 20BQwen 3 14BPixtral Large 124BNemotron Cascade 2 30B A3B
Phi-4-reasoning-plus 14BNemotron 3 Nano 30BLeanstral 119B A6BDevstral Small 1.1Phi-4 Mini Reasoning 4B
Gemma 4 31BNemotron Nano 8BMinistral 3 14B
EXAONE 4.0 32B
Jina Embeddings v3
BGE M3Qwen 3.5 397B A17B
Kimi K2.5Kimi K2.6
DeepSeek V4 ProDeepSeek V4 Flash
GLM-5.2GLM-5.1GLM-5DeepSeek V3.2Qwen 3 235B A22BQwen3-Coder 480B A35B InstructDeepSeek Coder V2 236BDeepSeek R1 671BDeepSeek V3.1 671BCasi al alcance
Modelos de alta calidad que necesitan un poco más de memoria
Image & Video Generation
55 of 56 models can generate images or video on your NVIDIA DGX Spark 128GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | ~8.9s | S |
| Stable Diffusion 1.5Image | 512×768 | ~17.8s | S |
| Realistic Vision v5.1Image | 512×768 | ~17.8s | S |
| DreamShaper 8Image | 512×768 | ~17.8s | S |
| LCM DreamShaper v7Image | 512×768 | ~5.3s | S |
| PixArt-SigmaImage | 1024×1024 | ~1m 11s | S |
| FramePack I2VVideo | 1280×720 | ~2m 11s/frame | S |
| SDXL TurboImage | 512×512 | ~8.9s | S |
| SDXL LightningImage | 1024×1024 | ~26.7s | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~1m 11s | S |
| Playground v2.5Image | 1024×1024 | ~1m 47s | S |
| RealVisXL v5.0Image | 1024×1024 | ~1m 20s | S |
| DreamShaper XLImage | 1024×1024 | ~1m 20s | S |
| Juggernaut XL v9Image | 1024×1024 | ~1m 20s | S |
| Animagine XL 3.1Image | 1024×1024 | ~1m 20s | S |
| Pony Diffusion V6 XLImage | 1024×1024 | ~1m 20s | S |
| Animagine XL 4.0Image | 1024×1024 | ~1m 20s | S |
| Illustrious XLImage | 1024×1024 | ~1m 20s | S |
| Wan Video 2.1 1.3BVideo | 480×832 | ~52s/frame | S |
| Stable Diffusion 3.5 MediumImage | 1024×1024 | ~2m 5s | S |
| Flux.2 Klein 4BImage | 1024×1024 | ~21.4s | S |
| LTX Video 2BVideo | 1280×720 | ~1m 2s/frame | S |
| KolorsImage | 1024×1024 | ~2m 22s | S |
| Stable CascadeImage | 1024×1024 | ~2m 58s | S |
| AuraFlow v0.3Image | 1536×1536 | ~5m 21s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~6m 32s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | ~1m 11s | S |
| CogVideoX 2BVideo | 720×480 | ~1m 2s/frame | S |
| HunyuanVideoVideo | 720×1280 | ~2m 11s/frame | S |
| ChromaImage | 1024×1024 | ~1m 11s | S |
| Z-Image TurboImage | 1536×1536 | ~1m 14s | S |
| Flux.1 DevImage | 1024×1024 | ~5m 21s | S |
| Flux.1 SchnellImage | 1024×1024 | ~1m 2s | S |
| LTX Video 13BVideo | 1280×720 | ~2m 11s/frame | S |
| Flux.1 Kontext DevImage | 1024×1024 | ~5m 56s | S |
| AnimateDiff v1.5.3Video | 512×768 | ~32.5s/frame | S |
| Cosmos Diffusion 7BVideo | 1024×576 | ~1m 42s/frame | S |
| CogVideoX 5BVideo | 720×480 | ~1m 29s/frame | S |
| Wan2.2 TI2V 5BVideo | 832×480 | ~1m 29s/frame | S |
| Flux.2 Klein 9BImage | 1024×1024 | ~35.6s | S |
| Flux.1 Fill DevImage | 1024×1024 | ~5m 3s | S |
| Krea 2Image | 1024×1024 | ~1m 37s | S |
| Sulphur 2Video | 1280×720 | ~1m 53s/frame | S |
| Ideogram 4Image | 2048×2048 | ~1m 28s | S |
| Mochi 1 PreviewVideo | 848×480 | ~1m 58s/frame | S |
| HunyuanVideo 1.5Video | 720×1280 | ~1m 49s/frame | S |
| Helios 14BVideo | 1280×720 | ~2m 15s/frame | S |
| SkyReels V2 14BVideo | 1280×720 | ~2m 15s/frame | S |
| Wan Video 2.1 14BVideo | 720×1280 | ~2m 15s/frame | S |
| Wan Video 2.2 14BVideo | 720×1280 | ~2m 15s/frame | S |
| Qwen ImageImage | 1024×1024 | ~1m 60s | S |
| Qwen Image EditImage | 1024×1024 | ~1m 60s | S |
| LTX-2 22BVideo | 1920×1088 | ~2m 41s/frame | S |
| Flux.2 DevImage | 1024×1024 | ~56m 10s | S |
| MAGI-1Video | 1280×720 | ~2m 47s/frame | S |
| HunyuanImage 3.0Image | 256×256 | ~3m 31s | 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
Opciones de mejora
NVIDIA H200 141GBSiguiente nivelDesbloquea 2 modelos adicionales que hoy no caben en tu setup.
Eleva la velocidad media de decodificación en torno a un 450% en los modelos que sí caben.
~$30,000 MSRP
NVIDIA B200 180GBMejora NVIDIADesbloquea 8 modelos adicionales que hoy no caben en tu setup.
Eleva la velocidad media de decodificación en torno a un 586% en los modelos que sí caben.
~$30,000 MSRP
Desbloquea 12 modelos adicionales que hoy no caben en tu setup.
Eleva la velocidad media de decodificación en torno a un 462% en los modelos que sí caben.
~$20,000 MSRP
Desbloquea 13 modelos adicionales que hoy no caben en tu setup.
Eleva la velocidad media de decodificación en torno a un 537% en los modelos que sí caben.
~$8,000 MSRP
NVIDIA DGX Spark 128GB (128 GB unified memory) can run these top models: Qwen 3.5 122B A10B (score: 88/100), Qwen3-Coder-Next (score: 88/100), Qwen3-Coder 30B A3B Instruct (score: 87/100). See the full compatibility list above.
NVIDIA DGX Spark 128GB ships with 128 GB of unified memory, with roughly 108.8 GB realistically usable for AI inference after OS and runtime overhead.
Yes, NVIDIA DGX Spark 128GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on NVIDIA DGX Spark 128GB, we recommend Qwen3-Coder-Next. It achieves 2.0 tokens per second with 4K context window. Qwen3-Coder-Next is a specialized fit for Coding. It is a recent-generation family, which helps on current local SOTA workloads. It is likely to require compromise or offload. Context is capped below the requested workload target (4096 vs 16000). Known distribution channels: huggingface, ollama, lm-studio.
There are 4 upgrade path(s) from NVIDIA DGX Spark 128GB: NVIDIA H200 141GB, NVIDIA B200 180GB. Upgrading would unlock larger models and faster inference speeds.
Yes, NVIDIA DGX Spark 128GB with 109 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.
NVIDIA DGX Spark 128GB (128 GB unified memory) 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.
NVIDIA DGX Spark 128GB is excellent for AI image generation. With 109 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, NVIDIA DGX Spark 128GB with 109 GB of usable memory can run Qwen 3.5 27B at Q8 (near-lossless, ~28.9 GB) or even FP16 (~55.4 GB) depending on your context needs. This setup provides an excellent experience with this model. Use Ollama or vLLM for best results.
With 109 GB VRAM on NVIDIA DGX Spark 128GB, use Q8_0 for most models — it is near-lossless and you have the memory for it. For 70B+ models, Q6_K offers excellent quality. Reserve Q4_K_M for 100B+ models or when you need maximum context length.
NVIDIA DGX Spark 128GB 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
