Qwen3-235B-A22B: What PC You Need
Qwen3-235B-A22B needs about 165.8GB at Q4. No PC we track with a verified price runs it comfortably.
Updated
What Qwen3-235B-A22B asks of a PC
Qwen3-235B-A22B is a mixture-of-experts model with 235B parameters, 22B of them active per token. Every expert has to stay resident, so its memory need follows the 235B figure, not the 22B one.
At 8K context Qwen3-235B-A22B takes 165.8GB at Q4, 225GB at Q6 and 289.1GB at Q8. Stepping from Q4 to Q8 costs 123.3GB.
Qwen3-235B-A22B accepts up to 32,768 tokens of context, and a long context adds memory: at 128K and Q4 it takes 195.8GB.
0 tracked PCs with a verified price run Qwen3-235B-A22B comfortably and 1 run it with limits.
Memory requirements for Qwen3-235B-A22B
| Quantization | 8K context | 32K context | 128K context |
|---|---|---|---|
| Q4 | 165.8GB | 171.8GB | 195.8GB |
| Q5 | 194.6GB | 200.6GB | 224.6GB |
| Q6 | 225GB | 231GB | 255GB |
| Q8 | 289.1GB | 295.1GB | 319.1GB |
- Parameters
- 235B
- Active per token
- 22B
- Context window
- 32,768
- Source
- Model card
Cheapest PCs that run Qwen3-235B-A22B comfortably
None we track with a verified price.
Cheapest PCs that run Qwen3-235B-A22B with limitations
| # | System | Type | AI Memory | GPU/NPU | AI Score | Price | Verified | View |
|---|---|---|---|---|---|---|---|---|
| 1 |  Framework Desktop (Ryzen AI Max+ PRO 495) | Desktop | 144GB | Radeon 8060S (40 CU) | 46.1 | Price awaiting re-verification | Check Price at Framework → |