Cherry ServersCloud ARM VDS 12 · 12 vCPU · 56 GB
Arm64 VDS · dedicated vCPU
Cherry Servers Cloud ARM VDS 12 costs $102.70/mo for 12 vCPU, 56 GB of RAM and 300 GB NVMe, cheaper than 29% of the 524 VPS plans we track, checked 16 Sept 2026.
Price
$102.70/mo
billed €89/mo
$0.1754/hour
$1.83 per GB RAM
Cheaper than 29% of tracked offers
Specs vs the whole index
- RAM
- 56 GB> 96% of offers
- vCPU
- 12 dedicated> 89% of offers
- Disk
- 300 GB NVMe> 78% of offers
- Bandwidth
- 20 TB/mo
Excl. VAT · standard monthly rate (longer terms are discounted) · 12 vCPU on 12 dedicated cores (12 x AmpereONE A192-32X)
Value score
80/100
- RAM · 56 GB
- 56.0
- vCPU · 12
- 18.0
- Disk · 300 GB NVMe
- 12.0
- Traffic · 20 TB
- 6.0
- 92.0 points ÷ $102.70
- 0.90 per $
1 point per GB of RAM, 1.5 per vCPU, 1 per 25 GB of disk up to 500 GB (SSD × 0.8, HDD × 0.4), and 0.3 per TB of traffic up to 20 TB.
The score ranks 0.90 points per dollar against the 524 tracked VPS plans, whose median is 0.43. A higher score means more machine for the money.
Regions · 1
- Lithuania
Data provenance
Cherry Servers · Public API · api.cherryservers.com/v1/plans (virtual plans only)
Fetched 16 Sept 2026
Prices exclude VAT. Always confirm on the provider's site.
Where this sits in the market
At $102.70/mo, Cloud ARM VDS 12 · 12 vCPU · 56 GB is cheaper than 29% of the 524 VPS plans in our index. It delivers 56 GB of RAM at $1.83/GB, 66% below the $5.42/GB market median. Its value score of 80/100 ranks it #100 among VPS plans that include a disk, and it is the 22nd cheapest of Cherry Servers's 34 tracked plans.
Open models this box runs comfortably · CPU inference
how we compute this →- Llama 3.3 70B~0.8–1.7 tok/s
- DeepSeek-R1 Distill Llama 70B~0.8–1.7 tok/s
- Qwen3 32B~1.8–3.6 tok/s
- Qwen2.5-Coder 32B~1.8–3.6 tok/s
- DeepSeek-R1 Distill Qwen 32B~1.8–3.6 tok/s
- Gemma 3 27B~2.2–4.3 tok/s
- Mistral Small 3.2 24B~2.5–4.9 tok/s
- Devstral Small 24B~2.5–5 tok/s
Largest two per lineup that fit 56 GB with 20% headroom at Q4_K_M and an 8K context; speeds are bandwidth-bound estimates for 12 dedicated vCPU.
