Can the GeForce RTX 3090 (used) run Mistral Small 3.2 24B Instruct (2506)?
Fits comfortably at Q4_K_M.
Mistral Small 3.2 24B Instruct (2506) is 24B parameters. At Q4_K_M the weights are about 13.4 GiB; with the 1.5 GiB runtime reserve that is 14.9 GiB against the card's 24GB, leaving about 9.1 GiB for context.
All three quants
24GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 13.4 GiB | 14.9 GiB | Fits comfortably | 9.1 GiB |
| Q8_0near-lossless | 23.7 GiB | 25.2 GiB | Only with CPU offload | short 1.2 GiB |
| FP16full weights | 44.7 GiB | 46.2 GiB | Only with CPU offload | short 22.2 GiB |
Verdict rules: fits comfortably when weights plus reserve sit within 85% of VRAM; tight when they fit with little left for context; CPU offload when they exceed VRAM by up to 2x (runs, slowly, with layers in system RAM); no beyond that. The KV cache per token depends on the model's architecture and is not modelled here.
The numbers for this pairing
At Q4_K_M the weights take about 13.4 GiB; with the 1.5 GiB we set aside for the runtime that is 14.9 of the card's 24 GB, leaving about 9.1 GB for the context cache.
The cheapest card on our list that runs it comfortably at Q4 is the Radeon RX 7900 XTX at about $850, against about $1,800 for this card.
At about $1,800, this card costs roughly $75 per GB of VRAM.
Running it at its full 350 W board power for 4 hours a day would use about 42 kWh a month, about $7.73 at the US average residential rate of 18.4 cents per kWh (2026-05); real use sits below that ceiling.
Prices are the lowest current listings our tracker saw on Oct 7, 2026, since averages include premium variants; launch prices are marked where we have no listing.
Good match. Get the card.
The GeForce RTX 3090 (used) clears Mistral Small 3.2 24B Instruct (2506) at Q4_K_M. Live listings below; this page was rebuilt 2026-10-07.
Amazon links may earn us a commission. Prices move daily; the links open live listings.
About the model
Mistral Small 3.2 24B Instruct (2506) by Mistral AI: 131,072-token native context, text + vision, released 2025 under the Apache-2.0. Model card → · Hosted pricing on PicksByModel →