DeepSeek V3 on NVIDIA GeForce RTX 3090
NVIDIA GeForce RTX 3090 cannot run DeepSeek V3 at any quantization level. The 24 GB of VRAM is insufficient.
Model Size
671B
Device VRAM
24 GB
Bandwidth
936 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows DeepSeek V3 performance at a different quality level on NVIDIA GeForce RTX 3090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q2_K | — | — | ✗ Offload | Not Viable | estimated |
Notes
Q2_K
671B MoE model requires 115GB+ at Q2_K. 24GB insufficient. Would need 128GB+ unified memory.
About DeepSeek V3
DeepSeek V3 (671B) is a chat, coding, ai coding, reasoning, multi-purpose model. Massive MoE model rivaling GPT-4 class. Only ~37B parameters active per token despite 671B total. Requires multi-GPU or very large unified memory (128GB+ Apple Silicon at Q2/Q3). Not for casual home use — included for completeness and to show what the high end looks like.
View all DeepSeek V3 hardware options →About NVIDIA GeForce RTX 3090
NVIDIA GeForce RTX 3090 has 24 GB at 936 GB/s. Street price: $899.
See all models NVIDIA GeForce RTX 3090 can run →Builds with NVIDIA GeForce RTX 3090
Extreme AI Workstation
2x NVIDIA GeForce RTX 3090 (Used) · 128GB DDR5-5600 (4x32GB)
High-End Home AI Server
2x NVIDIA GeForce RTX 3090 24GB (Used) + NVLink Bridge · 128GB DDR5-5600 (4x32GB)
Mid-Range Home AI Server
NVIDIA GeForce RTX 3090 24GB (Used) · 64GB DDR5-5600 (2x32GB)
Source: Performance estimates based on model size and device bandwidth (2026-03-15)
Data last updated: 2026-03-15