Rent a GPU

Can the NVIDIA RTX 3070 run gpt-oss 20B?

RTX 3070 × gpt-oss 20B8K context
NoDoes not fit in memory
Memory at Q4_K_M13.5 GB of 8 GB
Weights 12.7 GBKV cache 0.2 GBRuntime 0.6 GB
On the GPU57%of the Q4_K_M weights
In system RAM5.5 GBthe rest spills over
Offload speed~32tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

No. Even at Q4_K_M, gpt-oss 20B needs about 13.5 GB, but the NVIDIA RTX 3070 has 8 GB usable. You could offload some layers to system RAM, but it will be very slow.

Try other context lengths

Run it on a rented GPU

On a cloud GPU with enough memory, the same command you'd use locally works:

ollama run gpt-oss:20b

At Q4_K_M it needs about 13.5 GB, so pick a GPU with at least 16 GB.

New to this? Step-by-step setup for the RTX 3070

Run it in the cloud

Too big for the NVIDIA RTX 3070? Run gpt-oss 20B on a rented GPU instead.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 8 GB the NVIDIA RTX 3070 can use.

QuantQualityMemoryFits?Speed
FP16Full quality42.6 GBToo big—
Q8_0Near-lossless23 GBToo big—
Q6_KExcellent17.9 GBToo big—
Q5_K_MVery good15.7 GBToo big—
Q4_K_MGood, most popular13.5 GBToo big—
Q3_K_MNoticeably degraded11 GBToo big—
Q2_KHeavily degraded8.6 GBToo big—

Measured speed from real RTX 3070 owners

Tokens per second that people measured on their own NVIDIA RTX 3070, next to our estimate.

No one has measured gpt-oss 20B on the NVIDIA RTX 3070 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 3070? Add your real speed

One command times gpt-oss 20B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- gpt-oss:20b

Windows (PowerShell)

$env:GPUFIT_MODEL="gpt-oss:20b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run gpt-oss 20B comfortably

Check RTX 4060 Ti 16GB prices

Models that run well on the NVIDIA RTX 3070

Frequently asked questions

Can NVIDIA RTX 3070 run gpt-oss 20B?

No. Even at Q4_K_M, gpt-oss 20B needs about 13.5 GB, but the NVIDIA RTX 3070 has 8 GB usable. You could offload some layers to system RAM, but it will be very slow.

How much VRAM does gpt-oss 20B need?

About 13.5 GB at Q4_K_M with 8,192 tokens of context, and about 42.6 GB at full FP16 precision.

How fast is gpt-oss 20B on the NVIDIA RTX 3070?

It does not fit in the NVIDIA RTX 3070's memory, so most layers would run from system RAM and generation would be very slow.