Rent a GPU

Can the NVIDIA RTX 4080 Super run Magistral Small 24B?

RTX 4080 Super × Magistral Small 24B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M13.5 GB of 16 GB
Weights 11.5 GBKV cache 1.3 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~38tokens per second
Max context22Ktokens that fit at Q3_K_M
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. Magistral Small 24B fits on the NVIDIA RTX 4080 Super at Q3_K_M, which costs noticeable quality. Expect about 38 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default magistral:24b download is Q4_K_M, which needs about 16.2 GB, more than the 16 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the RTX 4080 Super

Run it in the cloud

Want full quality? Run Magistral Small 24B on a bigger rented GPU.

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 16 GB the NVIDIA RTX 4080 Super 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 GBFits~38 tok/s
Q2_KHeavily degraded10.8 GBFits~50 tok/s

Measured speed from real RTX 4080 Super owners

Tokens per second that people measured on their own NVIDIA RTX 4080 Super, next to our estimate.

No one has measured Magistral Small 24B on the NVIDIA RTX 4080 Super yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 4080 Super? 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 4080 Super

Frequently asked questions

Can NVIDIA RTX 4080 Super run Magistral Small 24B?

Only just. Magistral Small 24B fits on the NVIDIA RTX 4080 Super at Q3_K_M, which costs noticeable quality. Expect about 38 tokens/second. A card with more memory is a better experience.

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 4080 Super?

Roughly 38 tokens per second at Q3_K_M, estimated from the NVIDIA RTX 4080 Super's 736 GB/s memory bandwidth.