Run gpt-oss-20b (MoE) on a VPS.
prices as of · Contabo as of · 163 of 524 plans fit, disk included · re-ranked daily
OpenAI's open-weight reasoner ships in MXFP4: ~13 GB on disk, 3.6B active, adjustable reasoning effort. Fits a 16 GB VPS. On a CPU-only VPS it needs about 14 GB of RAM: 12.1 GB of weights in the model's native format, 410 MB of KV cache for an 8,192-token context and 1.5 GB for the OS and runtime. 163 of the 524 plans in our index fit and include a disk; the cheapest comfortable pick is OVHcloud's VPS-4 2027 · 8 vCPU / 24 GB · EU at $27.11/mo, streaming an estimated 4.4–8.7 tok/s.
The cheapest VPS that runs gpt-oss-20b (MoE) is OVHcloud VPS-4 2027 at $27.11/mo, 24 GB of RAM against the 14 GB the model needs, checked 16 Sept 2026.
Best VPS plans for gpt-oss-20b (MoE)
ranked by estimated tokens/s per dollar, comfortable fits first
- 1runs comfortably~8.2–16 tok/s$38.71/moView at netcup ↗
- 2runs comfortably~4.4–8.7 tok/s$16.15/mochecked 10 days agoView at Contabo ↗
- 3runs comfortably~5.4–11 tok/s$28.85/mochecked 10 days agoView at Contabo ↗
- 4runs comfortably~5.4–11 tok/s$31.43/moView at netcup ↗
- 5runs comfortably~4.4–8.7 tok/s$27.11/moView at OVHcloud ↗
- 6runs comfortably~5.4–11 tok/s$34.03/monot available nowView at Hetzner ↗
Speed = effective memory bandwidth ÷ active weight bytes (4 GB/s per shared vCPU, 6 per dedicated, ×0.5 for MoE routing overhead), shown as a band. Real numbers depend on the host CPU generation, AVX-512/AMX support and how noisy the neighbors are, so treat these as order-of-magnitude estimates.
RAM needed · CPU inference
14 GB
- weights · native format
- 12.1 GB
- KV cache · 8K context
- 410 MB
- OS + runtime headroom
- 1.5 GB
Model card
- Size
- 21B total · 3.6B active
- Context
- 128K tokens
- Kind
- reasoning
- Released
- 2025-08
- License
- Apache-2.0
Facts fetched from Hugging Face on 7 Sept 2026: exact GGUF file sizes, KV geometry from the GGUF header · 6,493,903 downloads.
Or rent it as an API · 43 providers sell gpt-oss-20b
every price for gpt-oss-20b →OpenAI list price
$0.22/M tokens
Cheapest price we can explain
$0.16/M tokens
Kilo Gateway, read 16 Sept 2026
What the VPS price buys
169M tokens/mo
at $27.11/mo
Token prices are per million, three parts input to one part output, and exclude tax. 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.
Or buy hardware · 13 reference machines fit
all machines →- Raspberry Pi 5 (16 GB)16 GB · 17 GB/s · ~1–1.6 tok/s$305*= 11 mo of VPS
- GeForce RTX 5060 Ti 16 GB (card only)16 GB · 448 GB/s · ~53–82 tok/s$800*= 30 mo of VPS
- GeForce RTX 5070 Ti 16 GB (card only)16 GB · 896 GB/s · ~100+ tok/s$1,200*= 44 mo of VPS
- Mac mini (M6, 32 GB)32 GB · 153 GB/s · ~18–28 tok/s$1,299= 48 mo of VPS
- GeForce RTX 5080 16 GB (card only)16 GB · 960 GB/s · ~100+ tok/s$1,600*= 59 mo of VPS
- Framework Desktop (Ryzen AI Max+ 395, 64 GB)64 GB · 256 GB/s · ~31–47 tok/s$1,659*= 61 mo of VPS
Buy · per month
$8.78
$8.47 hardware + $0.31 power
Rent · per month
$27.11
OVHcloud VPS-4 2027 · 8 vCPU / 24 GB · EU
Break-even
The Raspberry Pi 5 (16 GB) pays for itself after 11 months of replacing the VPS, and it streams an estimated 1–1.6 tok/s against the VPS's CPU-only pace.
* approximate: August 2026 US retail median rather than list price. Local speed = peak bandwidth × 0.7 efficiency (0.35 on CPU-only boards) ÷ active weight bytes; unified-memory machines are assumed to give models 75% of their RAM. GPU cards need a host PC that is not included in the price.
Frequently asked
- How much RAM does gpt-oss-20b (MoE) need?
- About 14 GB for CPU inference at Q4_K_M: 12.1 GB of weights, 410 MB of KV cache at 8,192 tokens of context, and 1.5 GB of headroom. Longer contexts need more KV cache (48 KB per token for this model).
- What is the cheapest VPS that can run gpt-oss-20b (MoE)?
- OVHcloud VPS-4 2027 · 8 vCPU / 24 GB · EU (24 GB RAM, 8 vCPU) at $27.11/mo excl. VAT runs it comfortably as of 16 Sept 2026. HOSTKEY vm.v2-medium · 8 vCPU · 16 GB at $16.15/mo is a tight fit.
- How fast will gpt-oss-20b (MoE) run on a VPS without a GPU?
- Roughly 8.2–16 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.