Run gpt-oss-120b (MoE) on a VPS.
Prices checked
The cheapest VPS that runs gpt-oss-120b (MoE) is Leaseweb VPS 6 at $65.69 a month, with 120 GB of RAM for the 65.5 GB it needs, checked .
Best plans for gpt-oss-120b (MoE)
Most tokens per second for your money, comfortable fits first.
- 1
VPS 6 · 24 vCPU / 120 GB · US
Leaseweb · 24C · 120 GB · ~4.2–8.5 tok/s$65.69/mo - 2
VPS 6 · 24 vCPU / 120 GB · UK
Leaseweb · 24C · 120 GB · ~4.2–8.5 tok/s$69.93/mo - 3
VPS 6 · 24 vCPU / 120 GB · Europe
Leaseweb · 24C · 120 GB · ~4.2–8.5 tok/s$70.37/mo - 4
VPS 6 · 24 vCPU / 120 GB · Singapore
Leaseweb · 24C · 120 GB · ~4.2–8.5 tok/s$109.50/mo - 5$203.62/mo
- 6
VPS 6 · 24 vCPU / 120 GB · Australia
Leaseweb · 24C · 120 GB · ~4.2–8.5 tok/s$158.03/mo
netcup · 20C · 96 GB · ~6.3–13 tok/sWhat it needs
RAM needed
65.5 GB
CPU inference at native format
Weights
63.4 GB
native format
KV cache
614 MB
8K context
OS and runtime
1.5 GB
headroom
o4-mini-class reasoning in ~65 GB of MXFP4 weights with only 5B active, which makes the case for a 96–128 GB dedicated box.
- Size
- 117B total · 5.1B active
- Context
- 128K tokens
- Kind
- reasoning
- Released
- 2025-08
- License
- Apache-2.0
Facts from Hugging Face: exact GGUF file sizes, KV geometry from the GGUF header, 2,854,564 downloads.
Or rent it as an API
every price for gpt-oss-120b73 providers sell gpt-oss-120b.
OpenAI's own price
$0.26per M tokens
Cheapest price
$0.06per M tokens
Kilo Gateway
What the VPS price buys
1095M tokens a month
at $65.69 a month
Or rent a GPU
every price for the A100 80GB PCIe2 providers rent the A100 80GB PCIe, with 80 GB of GPU memory against the 65.5 GB gpt-oss-120b (MoE) needs.
Cheapest board that fits
A100 80GB PCIe
80 GB of GPU memory
On demand
$1.19per GPU an hour
RunPod
Held for a month
$868.70
730 hours of A100 PCIe · Community Cloud
At 19 million tokens a month, what this box generates in 730 hours at its estimated rate, the API costs you $1.12, this VPS $65.69 and the GPU $868.70. Above about 1,095 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 machines3 reference machines fit gpt-oss-120b (MoE).
Framework Desktop (Ryzen AI Max+ 395, 128 GB)
Approximate128 GB · 256 GB/s · ~24–36 tok/s
$3,449= 53 mo of VPSNVIDIA DGX Spark (128 GB)
Approximate128 GB · 273 GB/s · ~25–39 tok/s
$4,699= 72 mo of VPSMac Studio (M5 Ultra, 96 GB)
Tight fit96 GB · 1200 GB/s · ~100+ tok/s
$5,499= 84 mo of VPS
Buy · per month
$100.47
$95.81 hardware + $4.67 power
Rent · per month
$65.69
Leaseweb VPS 6 · 24 vCPU / 120 GB · US
Break-even
The Framework Desktop (Ryzen AI Max+ 395, 128 GB) pays for itself after 57 months of replacing the VPS, and it streams an estimated 24–36 tok/s against the VPS's CPU-only pace.
How we count
On a CPU-only VPS gpt-oss-120b (MoE) needs about 65.5 GB of RAM: 63.4 GB of weights in the model's native format, 614 MB of KV cache for an 8,192-token context and 1.5 GB for the OS and runtime. 9 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.
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, times 0.5 for MoE routing overhead), 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 $0.06 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 gpt-oss-120b (MoE) need?
- About 65.5 GB for CPU inference at Q4_K_M: 63.4 GB of weights, 614 MB of KV cache at 8,192 tokens of context, and 1.5 GB of headroom. Longer contexts need more KV cache (72 KB per token for this model).
- What is the cheapest VPS that can run gpt-oss-120b (MoE)?
- Leaseweb VPS 6 · 24 vCPU / 120 GB · US (120 GB RAM, 24 vCPU) at $65.69/mo excl. VAT runs it comfortably as of 31 Oct 2026.
- How fast will gpt-oss-120b (MoE) run on a VPS without a GPU?
- Roughly 4.2–8.5 tok/s on the top pick. Token generation is limited by memory bandwidth, because each new token reads the active experts' weights once. More vCPUs help, dedicated ones most, but a GPU or an Apple silicon machine is 10 to 50 times faster.
Same lineup
Same size class