Can the Radeon RX 9070 XT run Qwen3 235B-A22B?
Does not fit at Q4_K_M.
Qwen3 235B-A22B is 235B parameters (MoE; all experts resident). At Q4_K_M the weights are about 131.3 GiB; with the 1.5 GiB runtime reserve that is 132.8 GiB against the card's 16GB, about 116.8 GiB more than the card has.
All three quants
16GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 131.3 GiB | 132.8 GiB | Does not fit | short 116.8 GiB |
| Q8_0near-lossless | 232.0 GiB | 233.5 GiB | Does not fit | short 217.5 GiB |
| FP16full weights | 437.7 GiB | 439.2 GiB | Does not fit | short 423.2 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 131.3 GiB, so with the 1.5 GiB runtime reserve it needs 132.8 GB: 116.8 GB more than the card's 16 GB.
No version of it fits entirely in this card's memory, so it would lean on system RAM and run far slower.
It is a mixture-of-experts model: about 22B of its 235B parameters work on each token, which helps speed, but all of them still have to fit in memory.
At about $810, this card costs roughly $51 per GB of VRAM.
Running it at its full 304 W board power for 4 hours a day would use about 36 kWh a month, about $6.71 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.
Not this card. These fit it comfortably at Q4.
Nothing in the consumer catalog fits Qwen3 235B-A22B at Q4 on a single card; this is multi-GPU or datacenter territory, or a job for hosted inference (see PicksByModel for per-token pricing).
What the Radeon RX 9070 XT does run well → · Qwen3 235B-A22B on every card →
About the model
Qwen3 235B-A22B by Alibaba Qwen: 32,768-token native context, text, released 2025 under the Apache-2.0. Model card → · Hosted pricing on PicksByModel →