Rent a GPU

Can the NVIDIA RTX 3080 10GB run Magistral Small 24B?

RTX 3080 10GB × Magistral Small 24B8K context
NoDoes not fit in memory
Memory at Q4_K_M16.2 GB of 10 GB
Weights 14.3 GBKV cache 1.3 GBRuntime 0.6 GB
On the GPU56%of the Q4_K_M weights
In system RAM6.2 GBthe rest spills over
Offload speed~5.2tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

No. Even at Q4_K_M, Magistral Small 24B needs about 16.2 GB, but the NVIDIA RTX 3080 10GB has 10 GB usable. You could offload some layers to system RAM, but it will be very slow.

Try other context lengths

Run it on a rented GPU

On a cloud GPU with enough memory, the same command you'd use locally works:

ollama run magistral:24b

At Q4_K_M it needs about 16.2 GB, so pick a GPU with at least 24 GB.

New to this? Step-by-step setup for the RTX 3080 10GB

Run it in the cloud

Too big for the NVIDIA RTX 3080 10GB? Run Magistral Small 24B on a rented GPU instead.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 10 GB the NVIDIA RTX 3080 10GB can use.

QuantQualityMemoryFits?Speed
FP16Full quality49.1 GBToo big—
Q8_0Near-lossless27 GBToo big—
Q6_KExcellent21.3 GBToo big—
Q5_K_MVery good18.7 GBToo big—
Q4_K_MGood, most popular16.2 GBToo big—
Q3_K_MNoticeably degraded13.5 GBToo big—
Q2_KHeavily degraded10.8 GBToo big—

Measured speed from real RTX 3080 10GB owners

Tokens per second that people measured on their own NVIDIA RTX 3080 10GB, next to our estimate.

No one has measured Magistral Small 24B on the NVIDIA RTX 3080 10GB yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 3080 10GB? Add your real speed

One command times Magistral Small 24B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- magistral:24b

Windows (PowerShell)

$env:GPUFIT_MODEL="magistral:24b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Magistral Small 24B comfortably

Check Radeon RX 7900 XT prices

Models that run well on the NVIDIA RTX 3080 10GB

Frequently asked questions

Can NVIDIA RTX 3080 10GB run Magistral Small 24B?

No. Even at Q4_K_M, Magistral Small 24B needs about 16.2 GB, but the NVIDIA RTX 3080 10GB has 10 GB usable. You could offload some layers to system RAM, but it will be very slow.

How much VRAM does Magistral Small 24B need?

About 16.2 GB at Q4_K_M with 8,192 tokens of context, and about 49.1 GB at full FP16 precision.

How fast is Magistral Small 24B on the NVIDIA RTX 3080 10GB?

It does not fit in the NVIDIA RTX 3080 10GB's memory, so most layers would run from system RAM and generation would be very slow.