Cheapest96 GB
8× RTX 3060
$0.59per hour
- Speed
- ~551 tok/sFaster than you read
- Per million tokens
- $0.30
Vast.ai · Marketplace · 99.7% reliable
Rent on Vast.aiLowest price per hour
Can the NVIDIA GeForce RTX 2080 Ti run gpt-oss-120b?
gpt-oss-120b · NVIDIA GeForce RTX 2080 Ti · 8,192 ctx · whole model residentQ2_K sizereconstructed size
IT DOES NOT FIT
No. Even Q2_K, the smallest format evaluated, needs 43.7 GB against 11 GB — short by 32.7 GB. No published file exists for this pair, so every size is rebuilt from the pinned architecture.
0/9formats that fit
11 GBdevice memory
43.7 GBneeded at smallest format
—speed unavailable: does not fit
616GB/s bandwidth
Run it in the cloud
Run gpt-oss-120b anyway, on a rented GPU
The NVIDIA GeForce RTX 2080 Ti cannot hold it, but these rented machines hold the whole model. The ones worth choosing between, priced live and billed by the second.
Your card Keeping about 61 GB of it in system RAM, the NVIDIA GeForce RTX 2080 Ti runs Q4_K_M at ~21 tokens per second (about reading pace) — free, if you have the RAM and the patience. The machines below hold all of it on the GPU. Size the offload →
Prices · 18:30 UTC, 22 Sept
Recommended128 GB
4× RTX 5090
$1.07per hour
- Speed
- ~1371 tok/sFaster than you read
- Per million tokens
- $0.22
Vast.ai · Marketplace · 99.6% reliable
Rent on Vast.aiLowest cost per token at 20+ tok/s
Fastest270 GB
1× B300
$7.89per hour
- Speed
- ~1473 tok/sFaster than you read
- Per million tokens
- $1.49
RunPod · Secure Cloud
Rent on RunPodHighest speed estimate
Compare all 18 rentable configurations →
No GPU at all
Use gpt-oss-120b by the token
- Novita AI$0.25 / M output · $0.050 / M inputOpen on Novita AI
- OpenRouter$0.60 / M output · $0.15 / M inputOpen on OpenRouter
Here the rented card is as cheap as the API or cheaper per token ($0.22 per million), and it keeps your data on a machine you control. The API is still the easier start: nothing to set up and nothing to switch off.
First time renting a GPU? How it works, in four steps
- Create an account and add credit. Both providers are prepaid: $10 is enough to try any card on this page for hours. A new RunPod account that arrives through a referral link gets a one-time $5 credit when it first adds $10.
- Pick the card and the count shown here, and a template: llama.cpp or vLLM for an OpenAI-compatible API, or one with a web chat if you only want to talk to the model. “How to launch it” below gives the exact image and command.
- Wait for the download. The weights are fetched on the machine; tens of gigabytes take a few minutes on a data-centre connection. You pay by the second from the moment it starts.
- Stop it when you are done. A running machine bills even when idle. A stopped one costs nothing per hour, though its disk is usually still billed until you delete it.
How to launch it
No Q4_K_M file of gpt-oss-120b is catalogued here, so there is no exact command to vouch for. Start the machine from the llama.cpp server image ghcr.io/ggml-org/llama.cpp:server-cuda and point -hf at a Q4_K_M build from the publisher or a quantizer you trust — search Hugging Face for one. Check its file size against the memory figure on this page before you rent.
Every machine holds the whole model at Q4_K_M and 8,192 tokens of context, no offload. Speeds are this site’s single-stream decode estimates; prices are what each provider’s own API quoted, on-demand, for the whole machine. Vast hosts below 98% measured reliability are left out.
Referral links Vast.ai, RunPod and Novita pay us a share of what you spend if you sign up through these buttons. It costs you nothing, and it never decides an order or a recommendation: both are computed from the live price and the speed, and options that pay us nothing are listed and recommended on the same terms. How we rank
Runs well on your NVIDIA GeForce RTX 2080 Ti instead
The models nearest to gpt-oss-120b — same lab first, then closest in size — that the NVIDIA GeForce RTX 2080 Ti holds whole at the standard format and runs at a usable speed. Nearest in size is not the same as equally good; compare them on the task you care about.
- LLaDA2.0-miniQ4_K_M · 11.0 GB · ~391 tok/s
- DeepSeek-Coder-V2-Lite-InstructQ4_K_M · 10.7 GB · ~277 tok/s
- DeepSeek-V2-LiteQ4_K_M · 10.7 GB · ~277 tok/s
- DeepSeek-V2-Lite-ChatQ4_K_M · 10.7 GB · ~277 tok/s
Every format evaluated
No published file exists for this pair, so every size is rebuilt from the pinned architecture. The Basis column says which is which for each row. Decode and first-token figures are calibrated estimates, not runs on this card.
| Format | Needs | Of 11 GB | Fits | Decode | First token | Basis |
|---|---|---|---|---|---|---|
| FP16 | 234.7 GB | 2134% | short by 223.7 GB | does not run | — | reconstructed size |
| Q8_0 | 125.2 GB | 1139% | short by 114.2 GB | does not run | — | reconstructed size |
| Q6_K | 97.0 GB | 881% | short by 86.0 GB | does not run | — | reconstructed size |
| Q5_K_M | 84.1 GB | 764% | short by 73.1 GB | does not run | — | reconstructed size |
| Q5_0 | 81.5 GB | 741% | short by 70.5 GB | does not run | — | reconstructed size |
| Q4_K_M | 71.9 GB | 654% | short by 60.9 GB | does not run | — | reconstructed size |
| Q4_0 | 67.0 GB | 609% | short by 56.0 GB | does not run | — | reconstructed size |
| Q3_K_M | 59.0 GB | 537% | short by 48.0 GB | does not run | — | reconstructed size |
| Q2_K | 43.7 GB | 397% | short by 32.7 GB | does not run | — | reconstructed size |
Sized at 8,192 tokens of context with the whole model resident — weights, the KV cache and the runtime reserve, offload off. Speed is only quoted for a format that fits: a rate for a configuration that cannot load is not a fact about anything.
Why the first-token figure is the same on every row
First token is modelled from the arithmetic the prompt requires, and that count does not change with the weight format — which is why it reads the same on every row. Real prefill does vary by format, because a quantized matmul is a different kernel; this model does not capture that, and the figure should be read as an order of magnitude rather than a ranking between formats.
What the labels mean
- published data
- Read from a published source — a file's byte count, a model's configuration or a manufacturer's specification — or exact arithmetic on such values. Not a measurement on a machine.
- reconstructed size
- Weight size reconstructed from the pinned architecture, because no published file exists.
- size range
- Only a lower and an upper bound are claimed for this weight size.
- estimate
- Calculated from sourced inputs by a stated method; an estimate, not a measurement.
Ways out
OPTION 1cluster
8× NVIDIA GeForce RTX 2080 Ti
8 of the same card, tensor parallel, holds it at Q2_K. Often cheaper than one larger card, and it is the option most sizing tools never mention.
OPTION 2larger device
NVIDIA RTX 6000 Ada Generation
48 GB holds it at Q2_K.
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
OPTION 3larger device
NVIDIA RTX PRO 5000 Blackwell 48GB
48 GB holds it at Q2_K.
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
OPTION 4larger device
AMD Radeon PRO W7900
48 GB holds it at Q2_K.
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
OPTION 5system RAM
Offload to system memory
Keeping some layers on the host lets it load at all, at a large cost in speed. The calculator sizes the split and prices it.
What this device does run
- Qwen3.5-9B 7.05 GB
- Qwen3.5-4B 3.98 GB
- gemma-4-12B-it 9.54 GB
- Qwen3.5-2B 2.32 GB
- gemma-4-E4B-it 5.86 GB
- NVIDIA-Nemotron-3-Nano-4B-BF16 3.46 GB
The full list is on the NVIDIA GeForce RTX 2080 Ti page.
Change anything
This page fixes the context at 8,192 tokens and one device. Batch, concurrent users, KV-cache format, clusters and rental cost are all in the calculator, already set to this pairing.
Open in the calculator →Everything the NVIDIA GeForce RTX 2080 Ti runsBest models for 11 GB
Where these numbers come from
gpt-oss-120b’s architecture is read from its publisher’s own config.json at a pinned revision, and the NVIDIA GeForce RTX 2080 Ti’s 11 GB comes from the specification; its 616 GB/s is a third-party figure, because the manufacturer no longer publishes it, so the speed here is an estimate built on an estimate. How far each figure can be trusted is published, per format and worst case included, on the accuracy scorecard.
Building this into your own product? A free API key returns exactly these figures, and the widget puts this answer on a product page with one script tag.
Use this answer in your own product
As JSON, from the API
curl -s https://llmbottleneck.com/v1/analyze \
-H "Authorization: Bearer $LLMB_KEY" -H "content-type: application/json" \
-d '{"model":"openai-gpt-oss-120b","quantization":"Q2_K","context":8192,"hardware":"nvidia-geforce-rtx-2080-ti"}'Same engine, same evidence, every field sourced. Free key in one step →
On your page, as a widget
<script src="https://llmbottleneck.com/widget.js" data-model="openai-gpt-oss-120b" data-quantization="Q2_K" data-hardware="nvidia-geforce-rtx-2080-ti" data-context="8192"></script>
No key needed. Unbranded, with your own buy button, on Pro and Business →