Which GPUs and Macs run DeepSeek R1 Distill Qwen 14B?
Key facts
DeepSeek R1 Distill Qwen 14B needs about 11 GB of graphics memory. It runs on 9 of the 10 graphics card setups on this page, such as the RTX 4060 Ti 16GB.
About 11.4 GB at Q4_K_M, our estimate. Checked . unsloth Q4_K_M GGUF.
The cheapest graphics card on our list that 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/sAnswers appear faster than you can read them.EU shops · Shown to visitors in Europe.
US shops · Shown to visitors outside Europe.
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.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
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
LIVE IN BROWSER · $0 · NO LOGIN
Test comparable open models (Recursive Flint 40B vs Gemma 4 31B) free in your browser
Open full 8-model playground ↗Click a starter prompt below or type your own question to watch Recursive Flint stream side by side against Gemma 4 31B right on this page:
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.
Which graphics cards run it
Seven popular graphics cards and two PCs with two cards each, at the standard quality (Q4). Click one for the full answer: memory, speed and price.
Runs well9
The whole model fits in the graphics memory.
Doesn't fit1
Not enough graphics memory: it needs about 11.4 GB. In a PC with enough normal memory it still runs, part of it from normal memory: Budget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card). Fast~26 tok/s
- RTX 3060 12GBhas 12 GB
Which Macs and mini PCs run it
Macs and mini PCs from the picker, at the standard quality (Q4). A Mac shares its memory with the rest of the computer. Each name opens that machine's page.
Runs well10
The whole model fits in the memory the graphics can use.
Runs slowly1
The whole model fits, but it answers slower than you read.
Doesn't fit1
Not enough shared memory: it needs about 11.4 GB.
- Mac mini M4 16GBhas 16 GB
Cheapest hardware for each size
From all 43 graphics cards, PCs and Macs on our list. "Runs slowly" means part of the model runs from normal memory: cheaper, but much slower. A smaller download needs less memory and answers a little less well.
- Standard quality (Q4_K_M)Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list)
- Standard quality (Q4_K_M), runs slowlyBudget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card)
- Smallest download (IQ2_XS)GeForce RTX 3060 12GB, $292€261, used (median of sold listings)
- Smallest download (IQ2_XS), runs slowlyNo machine on our list runs this size.
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.
Prices moved: see Building a local LLM rig in the RAMageddon.
About DeepSeek R1 Distill Qwen 14B
14.77B parameters. Parameter count is the published figure. More parameters usually means a smarter model that needs more memory.
- Licence:
- MIT source
- Longest conversation:
- about 197 pages of text (131,072 tokens)
- Input:
- text
- Released:
- source
Sources and method
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.
Ran DeepSeek R1 Distill Qwen 14B on your own hardware? Send us your llama-bench result.
Memory at each quality level
Each download of DeepSeek R1 Distill Qwen 14B is a different size. The total adds the file, the memory a conversation of about 12 pages of text (8,192 tokens) takes, and 0.8 GB of working space. A measured file size is labelled; the rest is our estimate. The last column is the cheapest machine that holds the total.
Swipe the table sideways to see every column, up to the cheapest machine.
| Quality (file) | File size | Conversation | Working space | Total | Cheapest machine that holds it |
|---|---|---|---|---|---|
| F16 | 29.55 GBmeasured GGUF | 1.6 GB | 0.8 GB | 32.0 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| Q8_0 | 15.70 GBmeasured GGUF | 1.6 GB | 0.8 GB | 18.1 GB | GeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings) |
| Q6_K | 12.12 GBmeasured GGUF | 1.6 GB | 0.8 GB | 14.5 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
| Q5_K_M | 10.51 GBmeasured GGUF | 1.6 GB | 0.8 GB | 12.9 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
| Q4_K_M | 8.99 GBmeasured GGUF | 1.6 GB | 0.8 GB | 11.4 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
| IQ4_XS | 8.12 GBmeasured GGUF | 1.6 GB | 0.8 GB | 10.5 GB | GeForce RTX 3060 12GB, $292€261, used (median of sold listings) |
| Q3_K_M | 7.34 GBmeasured GGUF | 1.6 GB | 0.8 GB | 9.8 GB | GeForce RTX 3060 12GB, $292€261, used (median of sold listings) |
| IQ3_XS | 6.38 GBmeasured GGUF | 1.6 GB | 0.8 GB | 8.8 GB | GeForce RTX 3060 12GB, $292€261, used (median of sold listings) |
| Q2_K | 5.77 GBmeasured GGUF | 1.6 GB | 0.8 GB | 8.2 GB | GeForce RTX 3060 12GB, $292€261, used (median of sold listings) |
| IQ2_XS | 4.70 GBmeasured GGUF | 1.6 GB | 0.8 GB | 7.1 GB | GeForce RTX 3060 12GB, $292€261, used (median of sold listings) |
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate
Questions
- Can I run DeepSeek R1 Distill Qwen 14B on 24GB?
- Yes, by our estimate. DeepSeek R1 Distill Qwen 14B needs about 11.4 GB at the standard quality, and a 24 GB card leaves about 23.4 GB usable.
- Can I run DeepSeek R1 Distill Qwen 14B on a 128GB Mac?
- Yes, by our estimate. DeepSeek R1 Distill Qwen 14B fits on Mac Studio M4 Max 128GB and Mac Studio M5 Max 128GB. Each leaves about 96.0 GB usable of its 128 GB.
- How fast is DeepSeek R1 Distill Qwen 14B on an RTX 5090?
- Fast: about 128 tokens per second (tok/s), our estimate. Answers appear faster than you can read them.