Can the GeForce RTX 5090 run Qwen3.6 35B-A3B?
Fits comfortably at Q4_K_M.
Qwen3.6 35B-A3B is 36B parameters (MoE; all experts resident). At Q4_K_M the weights are about 20.1 GiB; with the 1.5 GiB runtime reserve that is 21.6 GiB against the card's 32GB, leaving about 10.4 GiB for context.
All three quants
32GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 20.1 GiB | 21.6 GiB | Fits comfortably | 10.4 GiB |
| Q8_0near-lossless | 35.5 GiB | 37.0 GiB | Only with CPU offload | short 5.0 GiB |
| FP16full weights | 67.1 GiB | 68.6 GiB | Does not fit | short 36.6 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 Qwen3.6 35B-A3B 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
Qwen3.6 35B-A3B by Alibaba Qwen: 262,144-token native context, text + vision, released 2026 under the Apache-2.0. Model card → · Hosted pricing on PicksByModel →