Run Phi-4 14B on a VPS.
Prices checked
The cheapest VPS that runs Phi-4 14B is Leaseweb VPS 2 at $9.04 a month, with 16 GB of RAM for the 12.2 GB it needs, checked .
Best plans for Phi-4 14B
Most tokens per second for your money, comfortable fits first.
- 1
VPS 2 · 6 vCPU / 16 GB · Europe
Leaseweb · 6C · 16 GB · ~1.6–3.2 tok/s$9.04/mo - 2
VPS 2 · 6 vCPU / 16 GB · UK
Leaseweb · 6C · 16 GB · ~1.6–3.2 tok/s$9.63/mo - 3
VPS 2 · 6 vCPU / 16 GB · US
Leaseweb · 6C · 16 GB · ~1.6–3.2 tok/s$9.89/mo - 4
VPS 3 · 8 vCPU / 24 GB · Europe
Leaseweb · 8C · 24 GB · ~2.2–4.3 tok/s$14.07/mo - 5
VPS 2 · 6 vCPU / 16 GB · Singapore
Leaseweb · 6C · 16 GB · ~1.6–3.2 tok/s$11.18/mo - 6$17.86/mo
Hetzner · 8C · 16 GB · ~2.2–4.3 tok/sWhat it needs
RAM needed
12.2 GB
CPU inference at Q4_K_M
Weights
9.1 GB
Q4_K_M
KV cache
1.6 GB
8K context
OS and runtime
1.5 GB
headroom
Synthetic-data-trained 14B with standout STEM reasoning; short 16K context.
- Size
- 15B parameters
- Context
- 16K tokens
- Kind
- reasoning
- Released
- 2024-12
- License
- MIT
Facts from Hugging Face: exact GGUF file sizes, KV geometry from the GGUF header, 372,170 downloads.
Or rent it as an API
every price for Phi 410 providers sell Phi 4.
Microsoft's own price
$0.09per M tokens
Cheapest price
$0.07per M tokens
Kilo Gateway
What the VPS price buys
129M tokens a month
at $9.04 a month
Or rent a GPU
every GPU price1 provider rents the RTX A5000, with 24 GB of GPU memory against the 12.2 GB Phi-4 14B needs.
Cheapest board that fits
RTX A5000
24 GB of GPU memory
On demand
$0.16per GPU an hour
RunPod
Held for a month
$116.80
730 hours of RTX A5000 · Community Cloud
At 7.1 million tokens a month, what this box generates in 730 hours at its estimated rate, the API costs you $0.50, this VPS $9.04 and the GPU $116.80. Above about 129 million tokens a month the VPS costs less than the API, which is more than this box generates in a month.
Or buy hardware
all machines14 reference machines fit Phi-4 14B.
Raspberry Pi 5 (16 GB)
Approximate16 GB · 17 GB/s · ~0.5–0.8 tok/s
$305= 34 mo of VPSGeForce RTX 5060 Ti 16 GB (card only)
Approximate16 GB · 448 GB/s · ~27–41 tok/s
$456= 50 mo of VPSMac mini (M6, 16 GB)
Tight fit16 GB · 153 GB/s · ~9–14 tok/s
$899= 99 mo of VPSGeForce RTX 5070 Ti 16 GB (card only)
Approximate16 GB · 896 GB/s · ~53–81 tok/s
$1,190= 10+ yrs of VPSMac mini (M6, 32 GB)
32 GB · 153 GB/s · ~9–14 tok/s
$1,299= 10+ yrs of VPSGeForce RTX 5080 16 GB (card only)
Approximate16 GB · 960 GB/s · ~57–87 tok/s
$1,650= 10+ yrs of VPS
Buy · per month
$8.78
$8.47 hardware + $0.31 power
Rent · per month
$9.04
Leaseweb VPS 2 · 6 vCPU / 16 GB · Europe
Break-even
The Raspberry Pi 5 (16 GB) pays for itself after 35 months of replacing the VPS, and it streams an estimated 0.5–0.8 tok/s against the VPS's CPU-only pace.
How we count
On a CPU-only VPS Phi-4 14B needs about 12.2 GB of RAM: 9.1 GB of Q4_K_M weights, 1.6 GB of KV cache for an 8,192-token context and 1.5 GB for the OS and runtime. 176 of the 527 plans in the index fit and include a disk. A plan runs it comfortably with 20% headroom over the total, and is a tight fit with exactly enough.
Other quants: Q8_0 weights take 15.6 GB (near-lossless, about half of F16); F16 takes 29.3 GB.
The plans are ranked by estimated tokens per second per dollar, comfortable fits first. Speed is effective memory bandwidth divided by active weight bytes (4 GB/s per shared vCPU, 6 per dedicated), shown as a band. Real numbers depend on the host CPU generation, AVX-512 and AMX support and how noisy the neighbours are, so treat them as an order of magnitude.
Token prices are per million, blended 3 in : 1 out, before tax. A price below the maker's is listed only when the provider says why. A rented box costs the same whether or not you use it and runs whatever else you put on it; an API charges for what you send and nothing when you stop.
A GPU rate is per GPU for an hour, and the monthly figure is 730 hours of the whole instance at it, tax excluded. The token price is $0.07 per million, blended 3 in : 1 out, the cheapest price (Kilo Gateway), and the box is assumed busy every second of the month, which nothing is.
A machine tagged approximate is priced at the typical US street price in August 2026 rather than its maker's own price. Local speed is peak bandwidth times 0.7 efficiency (0.35 on CPU-only boards) divided by active weight bytes; unified-memory machines are assumed to give models 75% of their RAM. GPU cards need a host PC that is not in the price.
Frequently asked
- How much RAM does Phi-4 14B need?
- About 12.2 GB for CPU inference at Q4_K_M: 9.1 GB of weights, 1.6 GB of KV cache at 8,192 tokens of context, and 1.5 GB of headroom. Longer contexts need more KV cache (200 KB per token for this model).
- What is the cheapest VPS that can run Phi-4 14B?
- Leaseweb VPS 2 · 6 vCPU / 16 GB · Europe (16 GB RAM, 6 vCPU) at $9.04/mo excl. VAT runs it comfortably as of 31 Oct 2026.
- How fast will Phi-4 14B run on a VPS without a GPU?
- Roughly 1.6–3.2 tok/s on the top pick. Token generation is limited by memory bandwidth, because each new token reads all of the weights once. More vCPUs help, dedicated ones most, but a GPU or an Apple silicon machine is 10 to 50 times faster.
Same lineup