Qwen on NVIDIA Hopper

Can I run Qwen3 30B-A3B on an H100 SXM 80GB?

Yes. Qwen3 30B-A3B at Q4_K_M uses 18.8 GB of the 74.4 GB available on a H100 SXM 80GB, and runs at about 192 tokens per second. You can push the context to 128K.

Runs comfortably

18.8 GB of 74.4 GB · 25%
074 GB
Weights 17.3 GB
KV cache 0.8 GB
Runtime overhead 0.8 GB

Qwen3 30B-A3B at Q4_K_M leaves 55.6 GB spare on a H100 SXM 80GB. There is room to raise the context length or move up a quantisation level.

Generation192tok/s
Prompt processing62183tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of Qwen3 30B-A3B 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 56.9 GB 58.4 GB Runs comfortably 128K 136
INT8 / W8A8 8.50 30.1 GB 31.6 GB Runs comfortably 128K 170
Q8_0 (GGUF) 8.50 30.1 GB 31.6 GB Runs comfortably 128K 170
FP8 (E4M3) 8.00 28.4 GB 30.0 GB Runs comfortably 128K 172
Q6_K 6.56 23.3 GB 24.9 GB Runs comfortably 128K 181
Q5_K_M 5.67 20.2 GB 21.7 GB Runs comfortably 128K 187
Q5_K_S 5.52 19.6 GB 21.2 GB Runs comfortably 128K 188
Q4_K_M 4.85 17.3 GB 18.8 GB Runs comfortably 128K 192
Q4_K_S 4.58 16.3 GB 17.9 GB Runs comfortably 128K 194
Q4_0 4.55 16.2 GB 17.8 GB Runs comfortably 128K 194
AWQ 4-bit 4.25 16.0 GB 17.5 GB Runs comfortably 128K 195
GPTQ 4-bit 4.25 16.0 GB 17.5 GB Runs comfortably 128K 195
MXFP4 4.25 16.0 GB 17.5 GB Runs comfortably 128K 195
IQ4_XS 4.25 15.2 GB 16.7 GB Runs comfortably 128K 196
Q3_K_M 3.91 14.0 GB 15.5 GB Runs comfortably 128K 199
IQ3_M 3.70 13.3 GB 14.8 GB Runs comfortably 128K 201
IQ3_XXS 3.06 11.1 GB 12.6 GB Runs comfortably 128K 206
Q2_K 2.63 9.6 GB 11.1 GB Runs comfortably 128K 209
IQ2_XXS 2.06 7.6 GB 9.1 GB Runs comfortably 128K 214
IQ1_M 1.75 6.5 GB 8.0 GB Runs comfortably 128K 217

Also worth checking

Qwen3 30B-A3B 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