OpenAI on NVIDIA Hopper

Can I run gpt-oss 20B-A3.6B on an H100 SXM 80GB?

Yes. gpt-oss 20B-A3.6B at Q4_K_M uses 13.1 GB of the 74.4 GB available on a H100 SXM 80GB, and runs at about 470 tokens per second. You can push the context to 128K.

Runs comfortably

13.1 GB of 74.4 GB · 18%
074 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 61.3 GB spare on a H100 SXM 80GB. There is room to raise the context length or move up a quantisation level.

Generation470tok/s
Prompt processing57692tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of gpt-oss 20B-A3.6B on a H100 SXM 80GB

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 Runs comfortably 128K 225
INT8 / W8A8 8.50 20.4 GB 21.6 GB Runs comfortably 128K 350
FP8 (E4M3) 8.00 19.5 GB 20.6 GB Runs comfortably 128K 360
Q6_K 6.56 16.0 GB 17.1 GB Runs comfortably 128K 404
Q5_K_M 5.67 13.8 GB 15.0 GB Runs comfortably 128K 437
Q5_K_S 5.52 13.4 GB 14.6 GB Runs comfortably 128K 443
AWQ 4-bit 4.25 11.9 GB 13.1 GB Runs comfortably 128K 469
GPTQ 4-bit 4.25 11.9 GB 13.1 GB Runs comfortably 128K 469
MXFP4 4.25 11.9 GB 13.1 GB Runs comfortably 128K 469
Q4_K_M 4.85 11.9 GB 13.1 GB Runs comfortably 128K 470
Q4_K_S 4.58 11.3 GB 12.4 GB Runs comfortably 128K 482
Q4_0 4.55 11.2 GB 12.4 GB Runs comfortably 128K 483
IQ4_XS 4.25 10.5 GB 11.7 GB Runs comfortably 128K 497
Q3_K_M 3.91 9.7 GB 10.9 GB Runs comfortably 128K 515
IQ3_M 3.70 9.2 GB 10.4 GB Runs comfortably 128K 526
IQ3_XXS 3.06 7.8 GB 8.9 GB Runs comfortably 128K 563
Q2_K 2.63 6.8 GB 8.0 GB Runs comfortably 128K 591
IQ2_XXS 2.06 5.5 GB 6.7 GB Runs comfortably 128K 633
IQ1_M 1.75 4.8 GB 5.9 GB Runs comfortably 128K 658

Also worth checking

gpt-oss 20B-A3.6B on every GPU
Full hardware tableEverything that runs on a H100 SXM 80GB
Full model tableWhy the KV cache is the part that bites
Guide