Qwen on NVIDIA Ada
Can I run Qwen3 235B-A22B on an RTX 4070?
Not at Q4_K_M — it needs 135.1 GB against 10.5 GB available. No quantisation of this model fits on one card.
Won't fit
135.1 GB of 10.5 GB · 1289%0141 GB
Weights
132.8 GB
KV cache
1.5 GB
Runtime overhead
0.8 GB
Over the limit
124.6 GB
Short by 124.6 GB. You can run it with 5 of 94 layers on the RTX 4070 and the rest in system RAM, at roughly 2.96 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation2.96tok/s
Prompt processing550tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of Qwen3 235B-A22B on a RTX 4070
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 | — | 0.91 |
| INT8 / W8A8 | 8.50 | 232.3 GB | 234.6 GB | Won't fit | — | 1.72 |
| Q8_0 (GGUF) | 8.50 | 232.3 GB | 234.6 GB | Won't fit | — | 1.72 |
| FP8 (E4M3) | 8.00 | 218.9 GB | 221.2 GB | Won't fit | — | 1.82 |
| Q6_K | 6.56 | 179.5 GB | 181.8 GB | Won't fit | — | 2.21 |
| Q5_K_M | 5.67 | 155.2 GB | 157.5 GB | Won't fit | — | 2.54 |
| Q5_K_S | 5.52 | 151.1 GB | 153.4 GB | Won't fit | — | 2.62 |
| Q4_K_M | 4.85 | 132.8 GB | 135.1 GB | Won't fit | — | 2.96 |
| Q4_K_S | 4.58 | 125.5 GB | 127.8 GB | Won't fit | — | 3.14 |
| Q4_0 | 4.55 | 124.7 GB | 127.0 GB | Won't fit | — | 3.16 |
| AWQ 4-bit | 4.25 | 118.0 GB | 120.3 GB | Won't fit | — | 3.33 |
| GPTQ 4-bit | 4.25 | 118.0 GB | 120.3 GB | Won't fit | — | 3.33 |
| MXFP4 | 4.25 | 118.0 GB | 120.3 GB | Won't fit | — | 3.33 |
| IQ4_XS | 4.25 | 116.5 GB | 118.8 GB | Won't fit | — | 3.37 |
| Q3_K_M | 3.91 | 107.2 GB | 109.5 GB | Won't fit | — | 3.66 |
| IQ3_M | 3.70 | 101.5 GB | 103.8 GB | Won't fit | — | 3.85 |
| IQ3_XXS | 3.06 | 84.1 GB | 86.4 GB | Won't fit | — | 4.64 |
| Q2_K | 2.63 | 72.4 GB | 74.7 GB | Won't fit | — | 5.34 |
| IQ2_XXS | 2.06 | 56.9 GB | 59.2 GB | Won't fit | — | 6.74 |
| IQ1_M | 1.75 | 48.4 GB | 50.7 GB | Won't fit | — | 7.84 |