Can the NVIDIA RTX 5080 run Mistral Small 24B?

Yes, with heavy quantization
QuantQ3_K_MNoticeably degraded
Memory13.5 GBof 16 GB
Speed~50tokens/s

Only just. Mistral Small 24B fits on the NVIDIA RTX 5080 at Q3_K_M, which costs noticeable quality. Expect about 50 tokens/second. A card with more memory is a better experience.

Try other context lengths in the calculator →
Run it in the cloud

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

Rent a cloud GPU by the hour. No upfront cost, cancel any time.

RunPodOn-demand GPUs with ready-made templates for Ollama and vLLM.Rent a GPU on RunPod → Vast.aiA marketplace of rentable GPUs, from RTX cards to H100s.Rent a GPU on Vast.ai →

Memory needed by quantization

At 8,192 tokens of context.

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~50 tok/s
Q2_KHeavily degraded10.8 GBFits~65 tok/s

How to run Mistral Small 24B on the NVIDIA RTX 5080

Ollama's default mistral-small: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.

GPUs that run Mistral Small 24B comfortably

Check NVIDIA RTX 3090 prices →

Models that run well on the NVIDIA RTX 5080