picksbycard
August 23, 2026No. 113
GeForce RTX 5090 ยท 32GB GDDR7

Can the GeForce RTX 5090 run DeepSeek R1 Distill Qwen 32B?

Fits comfortably at Q4_K_M.

DeepSeek R1 Distill Qwen 32B is 32.8B parameters. At Q4_K_M the weights are about 18.3 GiB; with the 1.5 GiB runtime reserve that is 19.8 GiB against the card's 32GB, leaving about 12.2 GiB for context.

All three quants

32GB card
QuantWeightsWith reserveVerdictHeadroom
Q4_K_Mthe everyday quant18.3 GiB19.8 GiBFits comfortably12.2 GiB
Q8_0near-lossless32.4 GiB33.9 GiBOnly with CPU offloadshort 1.9 GiB
FP16full weights61.1 GiB62.6 GiBOnly with CPU offloadshort 30.6 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.

Good match. Get the card.

The GeForce RTX 5090 clears DeepSeek R1 Distill Qwen 32B at Q4_K_M. Live listings below; this page was rebuilt 2026-08-23.

Amazon links may earn us a commission. Prices move daily; the links open live listings.

About the model

DeepSeek R1 Distill Qwen 32B by DeepSeek: 131,072-token native context, text, released 2025 under the MIT. Model card →

The Silicon Note

One short read on the GPU market, most mornings. No spam, one-click out.