OpenAI on NVIDIA Ada
Can I run gpt-oss 20B-A3.6B on an RTX 4070?
Not at Q4_K_M — it needs 13.1 GB against 10.5 GB available. Drop to IQ3_M and it fits, at about 127 tokens per second.
Won't fit
13.1 GB of 10.5 GB · 125%014 GB
Weights
11.9 GB
KV cache
0.4 GB
Runtime overhead
0.8 GB
Over the limit
2.6 GB
Short by 2.6 GB. You can run it with 18 of 24 layers on the RTX 4070 and the rest in system RAM, at roughly 45.3 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation45.3tok/s
Prompt processing3383tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of gpt-oss 20B-A3.6B 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 | 38.9 GB | 40.1 GB | Won't fit | — | 6.71 |
| INT8 / W8A8 | 8.50 | 20.4 GB | 21.6 GB | Won't fit | — | 15.8 |
| FP8 (E4M3) | 8.00 | 19.5 GB | 20.6 GB | Won't fit | — | 17.4 |
| Q6_K | 6.56 | 16.0 GB | 17.1 GB | Won't fit | — | 23.6 |
| Q5_K_M | 5.67 | 13.8 GB | 15.0 GB | Won't fit | — | 33.4 |
| Q5_K_S | 5.52 | 13.4 GB | 14.6 GB | Won't fit | — | 34.2 |
| AWQ 4-bit | 4.25 | 11.9 GB | 13.1 GB | Won't fit | — | 45.2 |
| GPTQ 4-bit | 4.25 | 11.9 GB | 13.1 GB | Won't fit | — | 45.2 |
| MXFP4 | 4.25 | 11.9 GB | 13.1 GB | Won't fit | — | 45.2 |
| Q4_K_M | 4.85 | 11.9 GB | 13.1 GB | Won't fit | — | 45.3 |
| Q4_K_S | 4.58 | 11.3 GB | 12.4 GB | Won't fit | — | 52.4 |
| Q4_0 | 4.55 | 11.2 GB | 12.4 GB | Won't fit | — | 52.7 |
| IQ4_XS | 4.25 | 10.5 GB | 11.7 GB | Won't fit | — | 70.1 |
| Q3_K_M | 3.91 | 9.7 GB | 10.9 GB | Won't fit | — | 85.9 |
| IQ3_M | 3.70 | 9.2 GB | 10.4 GB | Fits, but tight | 9K | 127 |
| IQ3_XXS | 3.06 | 7.8 GB | 8.9 GB | Runs comfortably | 41K | 145 |
| Q2_K | 2.63 | 6.8 GB | 8.0 GB | Runs comfortably | 62K | 160 |
| IQ2_XXS | 2.06 | 5.5 GB | 6.7 GB | Runs comfortably | 90K | 186 |
| IQ1_M | 1.75 | 4.8 GB | 5.9 GB | Runs comfortably | 105K | 204 |