DeepSeekDeepSeek R1 on NVIDIA GeForce RTX 4090
RTX 4090 cannot run DeepSeek R1. 24 GB VRAM is insufficient at any quantization level.
Model Size
671B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantization
Q2_K
Performance by Quantization
OwnRig currently has one published compatibility entry for DeepSeek R1 on NVIDIA GeForce RTX 4090 at Q2_K. This pairing has limitations — check the rating and notes below.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q2_K | 1 tok/s | 5000ms | ✗ Offload | Not viable | estimated |
Notes
Q2_K
671B MoE. Doesn't fit on single GPU. Use distilled versions instead.
About DeepSeek R1
DeepSeek R1 (671B) is a reasoning, coding, ai coding, multi-purpose model. DeepSeek's reasoning-focused model. Same MoE architecture as V3 (671B total, ~37B active per token). Excels at chain-of-thought reasoning, math, and complex code. Requires the same massive hardware as V3: multi-GPU or 128GB+ Apple Silicon at heavy quantization. For most home users, the distilled versions (7B, 32B) are more practical.
View all DeepSeek R1 hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Estimate method: Community benchmarks. Reference hardware source: github.com (2026-01-15)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.