Can the GeForce RTX 5090 run Qwen2.5 Coder 32B Instruct?
Fits comfortably at Q4_K_M.
Qwen2.5 Coder 32B Instruct is 32.5B parameters. At Q4_K_M the weights are about 18.2 GiB; with the 1.5 GiB runtime reserve that is 19.7 GiB against the card's 32GB, leaving about 12.3 GiB for context.
All three quants
32GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 18.2 GiB | 19.7 GiB | Fits comfortably | 12.3 GiB |
| Q8_0near-lossless | 32.1 GiB | 33.6 GiB | Only with CPU offload | short 1.6 GiB |
| FP16full weights | 60.5 GiB | 62.0 GiB | Only with CPU offload | short 30.0 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 18.2 GiB; with the 1.5 GiB we set aside for the runtime that is 19.7 of the card's 32 GB, leaving about 12.3 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 $6,500 for this card.
At about $6,500, this card costs roughly $203 per GB of VRAM.
Running it at its full 575 W board power for 4 hours a day would use about 69 kWh a month, about $12.70 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 5090 clears Qwen2.5 Coder 32B Instruct 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
Qwen2.5 Coder 32B Instruct by Alibaba Qwen: 32,768-token native context, text, released 2024 under the Apache-2.0. Model card → · Hosted pricing on PicksByModel →