Run Devstral Small 24B on a VPS.
Prices checked
The cheapest VPS that runs Devstral Small 24B is Leaseweb VPS 3 at $14.07 a month, with 24 GB of RAM for the 17.1 GB it needs, checked .
Best plans for Devstral Small 24B
Most tokens per second for your money, comfortable fits first.
- 1
VPS 3 · 8 vCPU / 24 GB · Europe
Leaseweb · 8C · 24 GB · ~1.3–2.7 tok/s$14.07/mo - 2
VPS 3 · 8 vCPU / 24 GB · US
Leaseweb · 8C · 24 GB · ~1.3–2.7 tok/s$17.99/mo - 3
VPS 3 · 8 vCPU / 24 GB · UK
Leaseweb · 8C · 24 GB · ~1.3–2.7 tok/s$18.08/mo - 4
VPS 4 · 12 vCPU / 48 GB · Europe
Leaseweb · 12C · 48 GB · ~1.7–3.4 tok/s$26.13/mo - 5
VPS 3 · 8 vCPU / 24 GB · Singapore
Leaseweb · 8C · 24 GB · ~1.3–2.7 tok/s$22.36/mo - 6
VPS 4 · 12 vCPU / 48 GB · US
Leaseweb · 12C · 48 GB · ~1.7–3.4 tok/s$31.49/mo
What it needs
RAM needed
17.1 GB
CPU inference at Q4_K_M
Weights
14.3 GB
Q4_K_M
KV cache
1.3 GB
8K context
OS and runtime
1.5 GB
headroom
Agentic coding model tuned for tool-using software agents (OpenHands, Cline).
- Size
- 24B parameters
- Context
- 128K tokens
- Kind
- code
- Released
- 2025-07
- License
- Apache-2.0
Facts from Hugging Face: exact GGUF file sizes, KV geometry from the GGUF header, 6,928 downloads.
Or rent a GPU
every GPU price1 provider rents the RTX A5000, with 24 GB of GPU memory against the 17.1 GB Devstral Small 24B needs.
Cheapest board that fits
RTX A5000
24 GB of GPU memory
On demand
$0.16per GPU an hour
RunPod
Held for a month
$116.80
730 hours of RTX A5000 · Community Cloud
Or buy hardware
all machines9 reference machines fit Devstral Small 24B.
Mac mini (M6, 32 GB)
32 GB · 153 GB/s · ~5.6–8.6 tok/s
$1,299= 92 mo of VPSMac mini (M5 Pro, 24 GB)
24 GB · 307 GB/s · ~11–17 tok/s
$1,699= 10+ yrs of VPSFramework Desktop (Ryzen AI Max+ 395, 64 GB)
Approximate64 GB · 256 GB/s · ~9.4–14 tok/s
$1,959= 10+ yrs of VPSMac mini (M5 Pro, 64 GB)
64 GB · 307 GB/s · ~11–17 tok/s
$2,299= 10+ yrs of VPSMac Studio (M5 Max, 36 GB)
36 GB · 460 GB/s · ~17–26 tok/s
$2,499= 10+ yrs of VPSGeForce RTX 5090 32 GB (card only)
Approximate32 GB · 1792 GB/s · ~66–101 tok/s
$3,440= 10+ yrs of VPS
Buy · per month
$37.45
$36.08 hardware + $1.36 power
Rent · per month
$14.07
Leaseweb VPS 3 · 8 vCPU / 24 GB · Europe
Break-even
The Mac mini (M6, 32 GB) pays for itself after 102 months of replacing the VPS, and it streams an estimated 5.6–8.6 tok/s against the VPS's CPU-only pace.
How we count
On a CPU-only VPS Devstral Small 24B needs about 17.1 GB of RAM: 14.3 GB of Q4_K_M weights, 1.3 GB of KV cache for an 8,192-token context and 1.5 GB for the OS and runtime. 94 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 25.1 GB (near-lossless, about half of F16); F16 takes 47.2 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 Devstral Small 24B need?
- About 17.1 GB for CPU inference at Q4_K_M: 14.3 GB of weights, 1.3 GB of KV cache at 8,192 tokens of context, and 1.5 GB of headroom. Longer contexts need more KV cache (160 KB per token for this model).
- What is the cheapest VPS that can run Devstral Small 24B?
- Leaseweb VPS 3 · 8 vCPU / 24 GB · Europe (24 GB RAM, 8 vCPU) at $14.07/mo excl. VAT runs it comfortably as of 31 Oct 2026.
- How fast will Devstral Small 24B run on a VPS without a GPU?
- Roughly 1.3–2.7 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.