NVIDIA DGX Spark — Local LLM Performance & Compatibility

Compact AI development desktop built around the GB10 Grace Blackwell Superchip — a 20-core Grace ARM CPU plus a Blackwell GPU (6,144 CUDA cores) sharing 128 GB of unified LPDDR5x memory at 273 GB/s. Runs the full CUDA stack, unlike Apple Silicon, making it ideal for fine-tuning and inference of 70B-class models. Launched at $3,999 in October 2025; price raised to $4,699 in February 2026 due to memory supply constraints.

Technical Specifications

VRAM128 GB
Memory Bandwidth273 GB/s
TDP150 W
ArchitectureGB10 Grace Blackwell Superchip
Release Year2025
MSRP at Launch$4,699
Inference Speed (Llama 3.1 8B Q4_K_M)~60 tokens/sec
Inference Speed (Llama 3.3 70B Q4_K_M)~20 tokens/sec
Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
NVIDIA DGX Spark (128GB)
Launch MSRP: $4,699
2026 prices are volatile — check the current listing.
Check price on Amazon

LLMs Compatible with 128 GB VRAM

All models below run comfortably in 128 GB VRAM with Q4_K_M quantization.

Llama 3.3Llama 3.3 70B Instruct · 43 GB VRAM · Q4_K_M · ollama run llama3.3
Llama 3.1 FamilyLlama 3.1 8B Instruct · 6 GB VRAM · Q4_K_M · ollama run llama3.1
Llama 4Llama 4 Scout 17B · 67 GB VRAM · Q4_K_M · ollama run llama4:scout
DeepSeek R1DeepSeek R1 Distill Qwen 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b
Qwen 3Qwen 3 235B-A22B (MoE) · 80 GB VRAM · Q4_K_M · ollama run qwen3:235b-a22b
Qwen3-CoderQwen3-Coder 80B-A3B (MoE) · 49 GB VRAM · Q4_K_M · ollama run qwen3-coder:80b-a3b-q4
Gemma 3Gemma 3 27B Instruct · 17 GB VRAM · Q4_K_M · ollama run gemma3:27b
Mistral Small 3.1Mistral Small 3.1 24B · 14 GB VRAM · Q4_K_M · ollama run mistral-small3.1

Best Use Cases

Quick Start with Ollama

Install Ollama then run the recommended model for this GPU:

ollama run llama3.3:70b

FAQ

Can the NVIDIA DGX Spark run local LLMs?

Yes — the NVIDIA DGX Spark has 128 GB VRAM and runs Compact AI development desktop built around the GB10 Grace Blackwell Superchip — a 20-core Grace ARM CPU plus a Blackwel

How fast is the NVIDIA DGX Spark for AI inference?

The NVIDIA DGX Spark runs Llama 3.1 8B at ~60 tokens/sec with Q4_K_M quantization. For the 70B model it achieves ~20 tokens/sec.

What LLMs can I run on 128 GB VRAM?

With 128 GB you can run: Llama 3.3, Llama 3.1 Family, Llama 4, DeepSeek R1, Qwen 3. Use Ollama for the easiest setup: ollama run llama3.3:70b.

Can I Run It? — NVIDIA DGX Spark

Compare Similar GPUs

VRAM Tier

Buying Guide

← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?