Can I run DeepSeek R1 Distill Qwen 14B on an RTX 5090?
Key facts
Yes. DeepSeek R1 Distill Qwen 14B runs on an RTX 5090, about 128 tokens per second (tok/s).
It needs about 11.4 GB at standard quality (estimate). Checked . unsloth Q4_K_M GGUF.
The cheapest graphics card on our list that holds it at Q4 is the Radeon RX 9060 XT 16GB. On an RTX 5090, at 32,768 tokens of context, it still fits in graphics memory (estimate).
How much memory it needs
It uses about 36% of the memory that is free on this card.
Get a 1-line alert when a faster quant for DeepSeek R1 Distill Qwen 14B drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new open-weight model fits 16 GB VRAM (11.4 GB at Q4 for DeepSeek R1 Distill Qwen 14B) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.
What an RTX 5090 costs
GeForce RTX 5090 32GB$6,816€7,367new (lowest in-stock EU)
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$6,816€7,367
How we priced this
New price, the lowest in stock in the EU.
Source: PriceSquirrel, checked 21 Oct 2026.
Cheapest in-stock listing on 21 Oct 2026: €7,367 for an INNO3D iChill Frostbite (water-cooled) at Alternate (Germany), found via PriceSquirrel. A cheaper €7,080 listing, an MSI Ventus 3X OC at Compumsa in Belgium, was out of stock.
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
The cheapest graphics card on our list that also runs it (it still needs the rest of a PC): Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list). Fast~23 tok/s
A complete machine that runs it at least as fast as you read: Mac Studio M4 Max 36GB, about $2,116€1,890 (used). Comfortable~18.5 tok/s
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
DeepSeek R1 Distill Qwen 14B on other graphics cards
Runs well9
The whole model fits in the graphics memory.
Doesn't fit1
Not enough graphics memory: it needs about 11.4 GB.
- RTX 3060 12GBhas 12 GB
More about the model itself, what it is good at and its licence: DeepSeek R1 Distill Qwen 14B.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Speed | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs | Fast~128 tok/s | 9.0 GBmeasured file | 1.6 GB | 0.8 GB | 11.4 GB | 31.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs | Fast~113 tok/s | 10.5 GB | 1.6 GB | 0.8 GB | 12.9 GB | 31.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Runs | Fast~79 tok/s | 15.8 GB | 1.6 GB | 0.8 GB | 18.2 GB | 31.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | — | 29.5 GB | 1.6 GB | 0.8 GB | 32.0 GB | 31.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs | Fast~89 tok/s | 9.0 GBmeasured file | 6.4 GB | 0.8 GB | 16.2 GB | 31.4 GB |
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . unsloth Q4_K_M GGUF.
DeepSeek's dense reasoning distill of DeepSeek-R1 onto Qwen2.5-14B, MIT licence. Hugging Face safetensors metadata lists 14,770,033,664 parameters (14.77B). 48 layers, 8 KV heads, head dim 128, context 131,072. The Q4_K_M GGUF is 8.99 GB (unsloth, 24 Oct 2026). At 8,192 tokens the rounded parts are 8.99 GB weights + 1.61 GB conversation memory + 0.80 GB working space = 11.40 GB, which equals the 11.4 GB usable line of a 12 GB card. The unrounded sum is a fraction over 11.4 GB, so the fit table does not mark Q4 as a full fit on 12 GB. IQ4_XS is an 8.12 GB file, about 10.53 GB in total at 8,192 tokens (our estimate), and that fits a 12 GB card. Only the 2-bit IQ2_XS file (4.70 GB, about 7.11 GB in total) fits an 8 GB card (about 7.4 GB usable). Ollama tag: deepseek-r1:14b.
Measured DeepSeek R1 Distill Qwen 14B on an RTX 5090 yourself? Send us your llama-bench result.
Questions
- Can I run DeepSeek R1 Distill Qwen 14B on an RTX 5090?
- Yes. DeepSeek R1 Distill Qwen 14B runs on an RTX 5090, about 128 tokens per second (tok/s).
- How much memory does DeepSeek R1 Distill Qwen 14B need?
- About 11.4 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 9.0 GB for the model file (measured), 1.6 GB to hold the conversation and 0.8 GB of working space.
- How fast is DeepSeek R1 Distill Qwen 14B on an RTX 5090?
- Fast: about 128 tokens per second (tok/s). Answers appear faster than you can read them. This is our estimate, not a measured test.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate