Qwen on NVIDIA Ampere
Can I run Qwen3 235B-A22B on an RTX 3090?
Not at Q4_K_M — it needs 135.1 GB against 21.8 GB available. You would need 7 of these cards.
Won't fit
135.1 GB of 21.8 GB · 621%0141 GB
Weights
132.8 GB
KV cache
1.5 GB
Runtime overhead
0.8 GB
Over the limit
113.4 GB
Short by 113.4 GB. You can run it with 13 of 94 layers on the RTX 3090 and the rest in system RAM, at roughly 3.36 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation3.36tok/s
Prompt processing673tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of Qwen3 235B-A22B on a RTX 3090
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 437.9 GB | 440.2 GB | Won't fit | — | 0.98 |
| INT8 / W8A8 | 8.50 | 232.3 GB | 234.6 GB | Won't fit | — | 1.87 |
| Q8_0 (GGUF) | 8.50 | 232.3 GB | 234.6 GB | Won't fit | — | 1.87 |
| FP8 (E4M3) | 8.00 | 218.9 GB | 221.2 GB | Won't fit | — | 2.00 |
| Q6_K | 6.56 | 179.5 GB | 181.8 GB | Won't fit | — | 2.46 |
| Q5_K_M | 5.67 | 155.2 GB | 157.5 GB | Won't fit | — | 2.85 |
| Q5_K_S | 5.52 | 151.1 GB | 153.4 GB | Won't fit | — | 2.95 |
| Q4_K_M | 4.85 | 132.8 GB | 135.1 GB | Won't fit | — | 3.36 |
| Q4_K_S | 4.58 | 125.5 GB | 127.8 GB | Won't fit | — | 3.58 |
| Q4_0 | 4.55 | 124.7 GB | 127.0 GB | Won't fit | — | 3.60 |
| AWQ 4-bit | 4.25 | 118.0 GB | 120.3 GB | Won't fit | — | 3.83 |
| GPTQ 4-bit | 4.25 | 118.0 GB | 120.3 GB | Won't fit | — | 3.83 |
| MXFP4 | 4.25 | 118.0 GB | 120.3 GB | Won't fit | — | 3.83 |
| IQ4_XS | 4.25 | 116.5 GB | 118.8 GB | Won't fit | — | 3.88 |
| Q3_K_M | 3.91 | 107.2 GB | 109.5 GB | Won't fit | — | 4.27 |
| IQ3_M | 3.70 | 101.5 GB | 103.8 GB | Won't fit | — | 4.54 |
| IQ3_XXS | 3.06 | 84.1 GB | 86.4 GB | Won't fit | — | 5.55 |
| Q2_K | 2.63 | 72.4 GB | 74.7 GB | Won't fit | — | 6.63 |
| IQ2_XXS | 2.06 | 56.9 GB | 59.2 GB | Won't fit | — | 8.88 |
| IQ1_M | 1.75 | 48.4 GB | 50.7 GB | Won't fit | — | 10.8 |