OpenAI on NVIDIA Ada

Can I run gpt-oss 20B-A3.6B on an RTX 4090?

Yes. gpt-oss 20B-A3.6B at Q4_K_M uses 13.1 GB of the 21.8 GB available on a RTX 4090, and runs at about 188 tokens per second. You can push the context to 128K.

Runs comfortably

13.1 GB of 21.8 GB · 60%
022 GB
Weights 11.9 GB
KV cache 0.4 GB
Runtime overhead 0.8 GB

gpt-oss 20B-A3.6B at Q4_K_M leaves 8.7 GB spare on a RTX 4090. There is room to raise the context length or move up a quantisation level.

Generation188tok/s
Prompt processing9625tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of gpt-oss 20B-A3.6B on a RTX 4090

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 38.9 GB 40.1 GB Won't fit — 10.2
INT8 / W8A8 8.50 20.4 GB 21.6 GB Fits, but tight 12K 123
FP8 (E4M3) 8.00 19.5 GB 20.6 GB Fits, but tight 32K 128
Q6_K 6.56 16.0 GB 17.1 GB Runs comfortably 107K 150
Q5_K_M 5.67 13.8 GB 15.0 GB Runs comfortably 128K 168
Q5_K_S 5.52 13.4 GB 14.6 GB Runs comfortably 128K 172
AWQ 4-bit 4.25 11.9 GB 13.1 GB Runs comfortably 128K 188
GPTQ 4-bit 4.25 11.9 GB 13.1 GB Runs comfortably 128K 188
MXFP4 4.25 11.9 GB 13.1 GB Runs comfortably 128K 188
Q4_K_M 4.85 11.9 GB 13.1 GB Runs comfortably 128K 188
Q4_K_S 4.58 11.3 GB 12.4 GB Runs comfortably 128K 196
Q4_0 4.55 11.2 GB 12.4 GB Runs comfortably 128K 196
IQ4_XS 4.25 10.5 GB 11.7 GB Runs comfortably 128K 206
Q3_K_M 3.91 9.7 GB 10.9 GB Runs comfortably 128K 217
IQ3_M 3.70 9.2 GB 10.4 GB Runs comfortably 128K 225
IQ3_XXS 3.06 7.8 GB 8.9 GB Runs comfortably 128K 253
Q2_K 2.63 6.8 GB 8.0 GB Runs comfortably 128K 276
IQ2_XXS 2.06 5.5 GB 6.7 GB Runs comfortably 128K 313
IQ1_M 1.75 4.8 GB 5.9 GB Runs comfortably 128K 338

Also worth checking

gpt-oss 20B-A3.6B on every GPU
Full hardware tableEverything that runs on a RTX 4090
Full model tableWhy the KV cache is the part that bites
Guide