Can I Run DeepSeek-R1-Distill-Qwen-32B on NVIDIA GeForce RTX 3090?
Written by Jakub Rusinowski · Last updated July 12, 2026
These figures are for DeepSeek-R1-Distill-Qwen-32B, a distill of Qwen2.5-32B — not the full DeepSeek R1. The full DeepSeek R1 (671B) needs about 405 GB of weights at Q4_K_M and is a different model.
Yes, but it's tight — DeepSeek R1 Distill Qwen 32B at Q4_K_M needs 22.3 GB at 8K context (19.3 GB weights + 3 GB KV cache/overhead), leaving ~1.7 GB of the NVIDIA GeForce RTX 3090's 24 GB, at ~27 tok/s (est.), with room for up to 8K context.
See what else this hardware can run →
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
NVIDIA GeForce RTX 3090 Specs
| VRAM | 24 GB |
| Memory Bandwidth | 936 GB/s |
DeepSeek R1 Distill Qwen 32B on the NVIDIA GeForce RTX 3090: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 66.9 GB | ✗ No | — | — |
| Q8_0 | 36.9 GB | ✗ No | — | Build for this |
| Q6_K | 29.2 GB | ✗ No | — | — |
| Q5_K_M | 25.6 GB | ✗ No | — | Build for this |
| Q4_K_M | 22.3 GB | ✓ Yes | 8K | Build for this |
| Q3_K_M | 16.6 GB | ✓ Yes | 32K | — |
| Q2_K | 13.5 GB | ✓ Yes | 32K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 24 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 3090: 8K 22.3 GB · 32K 28.7 GB ✗ · 128K 54.5 GB ✗. Past 32K it no longer fits 24 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? DeepSeek R1 Distill Qwen 32B on 32 GB of system RAM, CPU only: runs comfortably.
DeepSeek R1 Sizes That Fit the NVIDIA GeForce RTX 3090 (at 8K context)
| DeepSeek R1 Distill Qwen 32B | Q4_K_M · 22.3 GB at 8K context · ~27 tok/s (est.) |
| DeepSeek R1 Distill Qwen 14B | Q4_K_M · 10.6 GB at 8K context · ~56 tok/s (est.) |
| DeepSeek R1 Distill Llama 8B | Q4_K_M · 6.7 GB at 8K context · ~87 tok/s (est.) |
At 2 hrs/day, buying (~$1,499) beats renting at $0.34/hr after about 6.1 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA GeForce RTX 3090 enough to run DeepSeek R1 locally?
Yes, but it's tight — DeepSeek R1 Distill Qwen 32B at Q4_K_M needs 22.3 GB at 8K context (19.3 GB weights + 3 GB KV cache/overhead), leaving ~1.7 GB of the NVIDIA GeForce RTX 3090's 24 GB, at ~27 tok/s (est.), with room for up to 8K context.
What's the best DeepSeek R1 size for the NVIDIA GeForce RTX 3090?
DeepSeek R1 Distill Qwen 32B at Q4_K_M quantization needs 22.3 GB at 8K context (19.3 GB weights + 3 GB KV cache/overhead), estimated ~27 tokens/sec, up to 8K context.
Every DeepSeek R1 size on the NVIDIA GeForce RTX 3090
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| DeepSeek R1 (671B) | 406.5 GB | Does not fit | — |
| DeepSeek R1 Distill Qwen 14B | 10.6 GB | Runs | ~56 tok/s |
| DeepSeek R1 Distill Llama 8B | 6.7 GB | Runs | ~87 tok/s |
DeepSeek R1 on Other GPUs
Popular Models on the NVIDIA GeForce RTX 3090
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | DeepSeek R1 Model Page | NVIDIA GeForce RTX 3090 GPU Page | Check Your Hardware