Run DeepSeek-R1 Distill Llama 70B on a VPS.
Prices checked
The cheapest VPS that runs DeepSeek-R1 Distill Llama 70B is Leaseweb VPS 5 at $34.18 a month, with 64 GB of RAM for the 46.5 GB it needs, checked .
Best plans for DeepSeek-R1 Distill Llama 70B
Most tokens per second for your money, comfortable fits first.
- 1
VPS 5 · 16 vCPU / 64 GB · Europe
Leaseweb · 16C · 64 GB · ~0.6–1.1 tok/s$34.18/mo - 2
VPS 5 · 16 vCPU / 64 GB · UK
Leaseweb · 16C · 64 GB · ~0.6–1.1 tok/s$48.22/mo - 3
VPS 5 · 16 vCPU / 64 GB · US
Leaseweb · 16C · 64 GB · ~0.6–1.1 tok/s$50.39/mo - 4
VPS 5 · 16 vCPU / 64 GB · Singapore
Leaseweb · 16C · 64 GB · ~0.6–1.1 tok/s$62.05/mo - 5
VPS 8000 G12.5
netcup · 16C · 64 GB · ~0.6–1.1 tok/s$63/mo - 6
VPS 6 · 24 vCPU / 120 GB · US
Leaseweb · 24C · 120 GB · ~0.6–1.1 tok/s$65.69/mo
What it needs
RAM needed
46.5 GB
CPU inference at Q4_K_M
Weights
42.5 GB
Q4_K_M
KV cache
2.5 GB
8K context
OS and runtime
1.5 GB
headroom
Top-tier open reasoning; a 64 GB dedicated box is the entry ticket.
- Size
- 71B parameters
- Context
- 128K tokens
- Kind
- reasoning
- Released
- 2025-01
- License
- MIT
Facts from Hugging Face: exact GGUF file sizes, KV geometry from the GGUF header, 34,804 downloads.
Or rent a GPU
every price for the RTX A60003 providers rent the RTX A6000, with 48 GB of GPU memory against the 46.5 GB DeepSeek-R1 Distill Llama 70B needs.
Cheapest board that fits
RTX A6000
48 GB of GPU memory
On demand
$0.33per GPU an hour
RunPod
Held for a month
$240.90
730 hours of RTX A6000 · Community Cloud · interruptible from $0.41/GPU-hr
Or buy hardware
all machines5 reference machines fit DeepSeek-R1 Distill Llama 70B.
Framework Desktop (Ryzen AI Max+ 395, 64 GB)
Tight fit64 GB · 256 GB/s · ~3.1–4.8 tok/s
$1,959= 57 mo of VPSMac mini (M5 Pro, 64 GB)
Tight fit64 GB · 307 GB/s · ~3.8–5.8 tok/s
$2,299= 67 mo of VPSFramework Desktop (Ryzen AI Max+ 395, 128 GB)
Approximate128 GB · 256 GB/s · ~3.1–4.8 tok/s
$3,449= 101 mo of VPSNVIDIA DGX Spark (128 GB)
Approximate128 GB · 273 GB/s · ~3.4–5.1 tok/s
$4,699= 10+ yrs of VPSMac Studio (M5 Ultra, 96 GB)
96 GB · 1200 GB/s · ~15–23 tok/s
$5,499= 10+ yrs of VPS
Buy · per month
$59.09
$54.42 hardware + $4.67 power
Rent · per month
$34.18
Leaseweb VPS 5 · 16 vCPU / 64 GB · Europe
Break-even
The Framework Desktop (Ryzen AI Max+ 395, 64 GB) pays for itself after 66 months of replacing the VPS, and it streams an estimated 3.1–4.8 tok/s against the VPS's CPU-only pace.
How we count
On a CPU-only VPS DeepSeek-R1 Distill Llama 70B needs about 46.5 GB of RAM: 42.5 GB of Q4_K_M weights, 2.5 GB of KV cache for an 8,192-token context and 1.5 GB for the OS and runtime. 34 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 75 GB (near-lossless, about half of F16); F16 takes 141.1 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.
A GPU rate is per GPU for an hour, and the monthly figure is 730 hours of the whole instance at it, tax excluded.
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 DeepSeek-R1 Distill Llama 70B need?
- About 46.5 GB for CPU inference at Q4_K_M: 42.5 GB of weights, 2.5 GB of KV cache at 8,192 tokens of context, and 1.5 GB of headroom. Longer contexts need more KV cache (320 KB per token for this model).
- What is the cheapest VPS that can run DeepSeek-R1 Distill Llama 70B?
- Leaseweb VPS 5 · 16 vCPU / 64 GB · Europe (64 GB RAM, 16 vCPU) at $34.18/mo excl. VAT runs it comfortably as of 31 Oct 2026. Leaseweb VPS 4 · 12 vCPU / 48 GB · Europe at $26.13/mo is a tight fit.
- How fast will DeepSeek-R1 Distill Llama 70B run on a VPS without a GPU?
- Roughly 0.6–1.1 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 size class