The best GPU for running gpt-oss 20B (MoE) (2026)
Ranked from live rental prices and computed VRAM fit, not opinion. Every card is judged at Q4_K_M — the quantisation most people actually run — at 8k context, so it's a fair comparison. A card that can't fit gpt-oss 20B (MoE)at that quality isn't listed, because it could only run a crushed version.
Best value
NVIDIA RTX A4000
Best throughput per dollar among cards that fit.
Cheapest that runs it
NVIDIA RTX A4000
Lowest hourly rental that fits it — $0.066/hr, Q4_K_M.
No compromise
—
Most headroom and highest throughput.
Every card that runs it, ranked
Best quantisation each card fits at 8k context, with the cheapest live rental and a bandwidth-derived throughput estimate. Sorted by tokens/sec per dollar.
| GPU | VRAM | VRAM used | ~tok/s | Cheapest rental | tok/s per $ |
|---|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | 96 GB | 13 GB14% | — | $1.690 | — |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | 96 GB | 13 GB14% | — | — | — |
| NVIDIA RTX 6000 Ada Generation | 48 GB | 13 GB27% | — | $0.494 | — |
| AMD Radeon PRO W7900 | 48 GB | 13 GB27% | — | — | — |
| NVIDIA RTX A6000 | 48 GB | 13 GB27% | — | $0.330 | — |
| NVIDIA GeForce RTX 5090 | 32 GB | 13 GB41% | — | $0.402 | — |
| NVIDIA RTX 5000 Ada Generation | 32 GB | 13 GB41% | — | $0.336 | — |
| NVIDIA GeForce RTX 4090 | 24 GB | 13 GB54% | — | $0.334 | — |
| AMD Radeon RX 7900 XTX | 24 GB | 13 GB54% | — | — | — |
| NVIDIA GeForce RTX 3090 Ti | 24 GB | 13 GB54% | — | $0.120 | — |
| NVIDIA RTX A5000 | 24 GB | 13 GB54% | — | $0.160 | — |
| NVIDIA GeForce RTX 3090 | 24 GB | 13 GB54% | — | — | — |
How this ranking is made — and its limit
Fit and throughput are computed from gpt-oss 20B (MoE)'s own configuration with the engine behind our cost-to-run page (bits-per-weight validated to 0.7% median error). Rental prices are the cheapest live figure across the providers we track, last updated Sat, 10 Oct 2026 21:20:59 GMT.
The value column ranks renting, because that's what we can price precisely. If you're buyinga card, the fit and throughput columns are exactly what you need — but we don't publish a purchase-price value ranking, because we don't have verified street prices and won't invent them. For the buy-vs-rent decision itself, see the guides below.
Tokens/sec is a bandwidth-derived estimate, not a benchmark — we don't run our own hardware tests (editorial policy). This is a mixture-of-experts model without a known active-parameter count, so throughput is omitted rather than guessed.
Check it yourself
See exactly what fits, at any context length
Running gpt-oss 20B (MoE): common questions
How much VRAM do you need to run gpt-oss 20B (MoE)?
Can an RTX 4090 run gpt-oss 20B (MoE)?
Can an RTX 3090 run gpt-oss 20B (MoE)?
Can an RTX 4060 Ti 16GB run gpt-oss 20B (MoE)?
What's the cheapest way to run gpt-oss 20B (MoE)?
Before you buy
Cheapest RTX 4090 rental
Live per-hour 4090 prices on Vast and Runpod, the spot-vs-on-demand lever, and what a 24 GB card actually runs — the rent-a-card answer for everything in the 14B–32B class.
What --n-cpu-moe actually does
The trick that makes MoE models 5× faster — except it usually makes them slower, and the famous speedup only happens when the model didn't fit in the first place.
GLM-4.5-Air on local hardware
The consumer-runnable GLM: VRAM by quant, which cards and unified-memory boxes clear it, and what to expect from published numbers — the written companion to this page.
Cheapest way to run GLM in the cloud
Air on one 80 GB card, GLM-4.6 on two, GLM-5 on a pair of H200s — the multi-GPU maths with live, dated rental prices.