Memory-Optimized 2C · 16 GB · 50 GB
Memory-Optimized
Price
$84/mo
$0.1250/hour
$5.25 per GB RAM
Cheaper than 43% of tracked offers
Specs vs the whole index
- RAM
- 16 GB> 51% of offers
- vCPU
- 2 dedicated> 10% of offers
- Disk
- 50 GB NVME> 33% of offers
- Bandwidth
- 4 TB/mo
Value score
33/100
Percentile of RAM, vCPU, disk and bandwidth per dollar across all 280 tracked offers. Higher = more machine for the money.
Regions · 10
- New York City, US
- San Francisco, US
- Amsterdam, NL
- Singapore, SG
- London, GB
- Frankfurt, DE
- Toronto, CA
- Bangalore, IN
- Sydney, AU
- Atlanta, US
Data provenance
DigitalOcean · Public pricing page — digitalocean.com/pricing/droplets (embedded plan JSON)
Fetched 5 Sept 2026
Prices exclude VAT. Always confirm on the provider's site.
One-click via DigitalOcean Marketplace (1-Click Apps; WireGuard via the "VPN Server" app): Docker · WordPress · n8n · Coolify · Node.js · PostgreSQL · Nextcloud · Minecraft · WireGuard (+372-app catalog) matrix →
Where this sits in the market
At $84/mo, Memory-Optimized 2C · 16 GB · 50 GB is cheaper than 43% of the 280 VPS plans in our index. It delivers 16 GB of RAM at $5.25/GB — 13% below the $6/GB market median. Its value score of 33/100 ranks it #188 overall, and it is the 33rd cheapest of DigitalOcean's 70 tracked plans.
Open models this box runs comfortably · CPU inference
how we compute this →- Qwen3 14B~0.8–1.6 tok/s
- DeepSeek-R1 Distill Qwen 14B~0.8–1.6 tok/s
- Phi-4 14B~0.8–1.6 tok/s
- Mistral Nemo 12B~1–1.9 tok/s
- Gemma 3 12B~1–1.9 tok/s
- Qwen3 8B~1.5–2.9 tok/s
- DeepSeek-R1-0528 Qwen3 8B~1.5–2.9 tok/s
- Llama 3.1 8B~1.5–3 tok/s
Largest two per lineup that fit 16 GB with 20% headroom at Q4_K_M and an 8K context; speeds are bandwidth-bound estimates for 2 dedicated vCPU.