Can the NVIDIA RTX 4090 run Mistral Small 24B?
Yes
QuantQ6_KExcellent
Memory21.3 GBof 24 GB
Speed~31tokens/s
Yes. The NVIDIA RTX 4090 can run Mistral Small 24B fully in VRAM at Q6_K (excellent), using about 21.3 GB of the 24 GB available, at roughly 31 tokens/second.
Try other context lengths in the calculator →Memory needed by quantization
At 8,192 tokens of context.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 49.1 GB | Too big | — |
| Q8_0 | Near-lossless | 27 GB | Too big | — |
| Q6_K | Excellent | 21.3 GB | Fits | ~31 tok/s |
| Q5_K_M | Very good | 18.7 GB | Fits | ~36 tok/s |
| Q4_K_M | Good, most popular | 16.2 GB | Fits | ~42 tok/s |
| Q3_K_M | Noticeably degraded | 13.5 GB | Fits | ~52 tok/s |
| Q2_K | Heavily degraded | 10.8 GB | Fits | ~68 tok/s |
How to run Mistral Small 24B on the NVIDIA RTX 4090
With Ollama installed, one command downloads and starts it:
ollama run mistral-small:24bOllama's default download is Q4_K_M (about 16.2 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.
GPUs that run Mistral Small 24B comfortably
- NVIDIA RTX 3090 (24 GB)
- AMD Radeon RX 7900 XTX (24 GB)
- Apple M2 Pro (32GB)
- NVIDIA RTX 5090 (32 GB)
- Apple M4 Pro (48GB)
Models that run well on the NVIDIA RTX 4090
Run it in the cloud
Don't want to buy hardware? Run Mistral Small 24B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.