OpenAI on NVIDIA Ada

Can I run gpt-oss 20B-A3.6B on an RTX 4060 Ti 16GB?

Yes. gpt-oss 20B-A3.6B at Q4_K_M uses 13.1 GB of the 14.2 GB available on a RTX 4060 Ti 16GB, and runs at about 62.2 tokens per second. You can push the context to 33K.

Fits, but tight

13.1 GB of 14.2 GB · 92%
014 GB
Weights 11.9 GB
KV cache 0.4 GB
Runtime overhead 0.8 GB

This fits with almost nothing to spare. A background application claiming VRAM will push it over. Drop to the next quantisation down, or quantise the KV cache to Q8_0 — that halves the cache for no meaningful quality loss.

Generation62.2tok/s
Prompt processing2567tok/s
Max context33Ktokens
KV per 1K tokens0GB

Every quantisation of gpt-oss 20B-A3.6B on a RTX 4060 Ti 16GB

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 — 7.32
INT8 / W8A8 8.50 20.4 GB 21.6 GB Won't fit — 18.9
FP8 (E4M3) 8.00 19.5 GB 20.6 GB Won't fit — 20.9
Q6_K 6.56 16.0 GB 17.1 GB Won't fit — 30.6
Q5_K_M 5.67 13.8 GB 15.0 GB Won't fit — 44.6
Q5_K_S 5.52 13.4 GB 14.6 GB Won't fit — 50.3
AWQ 4-bit 4.25 11.9 GB 13.1 GB Fits, but tight 32K 62.1
GPTQ 4-bit 4.25 11.9 GB 13.1 GB Fits, but tight 32K 62.1
MXFP4 4.25 11.9 GB 13.1 GB Fits, but tight 32K 62.1
Q4_K_M 4.85 11.9 GB 13.1 GB Fits, but tight 33K 62.2
Q4_K_S 4.58 11.3 GB 12.4 GB Runs comfortably 46K 65.1
Q4_0 4.55 11.2 GB 12.4 GB Runs comfortably 48K 65.5
IQ4_XS 4.25 10.5 GB 11.7 GB Runs comfortably 63K 69.1
Q3_K_M 3.91 9.7 GB 10.9 GB Runs comfortably 79K 73.7
IQ3_M 3.70 9.2 GB 10.4 GB Runs comfortably 89K 76.9
IQ3_XXS 3.06 7.8 GB 8.9 GB Runs comfortably 121K 88.5
Q2_K 2.63 6.8 GB 8.0 GB Runs comfortably 128K 98.5
IQ2_XXS 2.06 5.5 GB 6.7 GB Runs comfortably 128K 116
IQ1_M 1.75 4.8 GB 5.9 GB Runs comfortably 128K 128

Also worth checking

gpt-oss 20B-A3.6B on every GPU
Full hardware tableEverything that runs on a RTX 4060 Ti 16GB
Full model tableWhy the KV cache is the part that bites
Guide