Run Llama 3.3 70B on a VPS.
September 2026 · 15 of 280 plans fit · re-ranked daily
Near-frontier quality from a dense 70B; needs a 64 GB box and patience on CPU. On a CPU-only VPS it 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. 15 of the 280 plans in our index fit; the cheapest comfortable pick is Contabo's Cloud VPS 16 · 16 vCPU · 64 GB at $43/mo, streaming an estimated 0.6–1.1 tok/s.
RAM needed · CPU inference
46.5 GB
- weights · Q4_K_M
- 42.5 GB
- KV cache · 8K context
- 2.5 GB
- OS + runtime headroom
- 1.5 GB
Other quants: Q8_0 weights 75 GB (near-lossless, about half of F16); F16 141.1 GB. Comfortable = 20% headroom over the total.
Model card
- Size
- 71B parameters
- Context
- 128K tokens
- Kind
- chat
- Released
- 2024-12
- License
- Llama 3.3 Community License
Facts fetched from Hugging Face on 3 Sept 2026: exact GGUF file sizes, KV geometry from the GGUF header · 627,558 downloads.
Best VPS plans for Llama 3.3 70B
ranked by estimated tokens/s per dollar, comfortable fits first
- 1runs comfortably~0.6–1.1 tok/s$43/mo
- 2runs comfortably~0.8–1.7 tok/s$69.70/mo
- 3runs comfortably~0.6–1.1 tok/s$46.83/mo
- 4runs comfortably~0.6–1.1 tok/s$91.81/mo
- 5runs comfortably~0.6–1.1 tok/s$115.06/mo
- 6runs comfortably~0.6–1.1 tok/s$233.82/mo
Speed = effective memory bandwidth ÷ 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/AMX support and how noisy the neighbours are — treat these as order-of-magnitude.
Or buy hardware · 5 reference machines fit
all machines →- Framework Desktop (Ryzen AI Max+ 395, 64 GB)64 GB · 256 GB/s · ~3.1–4.8 tok/s · tight$1,959= 46 mo of VPS
- Mac mini (M5 Pro, 64 GB)64 GB · 307 GB/s · ~3.8–5.8 tok/s · tight$2,299= 54 mo of VPS
- Framework Desktop (Ryzen AI Max+ 395, 128 GB)128 GB · 256 GB/s · ~3.1–4.8 tok/s$3,449= 80 mo of VPS
- NVIDIA DGX Spark (128 GB)128 GB · 273 GB/s · ~3.4–5.1 tok/s$4,699*= 109 mo of VPS
- Mac 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
$43
Contabo Cloud VPS 16 · 16 vCPU · 64 GB
Break-even
The Framework Desktop (Ryzen AI Max+ 395, 64 GB) pays for itself after 51 months of replacing the VPS — and it streams an estimated 3.1–4.8 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 Llama 3.3 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 Llama 3.3 70B?
- Contabo Cloud VPS 16 · 16 vCPU · 64 GB (64 GB RAM, 16 vCPU) at $43/mo excl. VAT runs it comfortably as of 5 Sept 2026. Contabo Cloud VPS 12 · 12 vCPU · 48 GB at $29.05/mo is a tight fit.
- How fast will Llama 3.3 70B run on a VPS without a GPU?
- Roughly 0.6–1.1 tok/s on the top pick. Token generation is bound by memory bandwidth — each token streams the full weights once — so more and dedicated vCPUs help; a GPU or Apple-silicon machine is 10–50× faster.