Skip to content
Run LLM Locally

gpt-oss-120b on the RTX 2080 Ti

gpt-oss-120b at MXFP4 needs about 63.2 GB: the RTX 2080 Ti (11 GB) cannot run it well, even with system RAM.

ShareFacebookXWhatsAppLinkedInEmail

gpt-oss-120b

MXFP4 · 8K context

Incompatible

The model needs about 63.2 GB; VRAM plus usable RAM give 61.9 GB. 1.3 GB are missing.

Your hardware
RTX 2080 Ti 11 GB · 64 GB RAM
Estimated memory
~63.2 GB estimate
VRAM (usable memory)
10.7 GB
GPU only
No
CPU/GPU offload
Required (51.2 GB)
Generation speed
Not available
Largest context in fast memory
None
Confidence: high

Memory breakdown

~63.2 GB (61.6 GB–64.8 GB) needed · estimate

Does not fit · 1.4 GB missing

  • Model weights59 GB
  • KV cache0.3 GB
  • Runtime overhead0.9 GB
  • Safety margin3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size · sliding-window layers keep 128 tokens

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • split CPU/GPU runs vary a lot with the CPU and PCIe link
  • system RAM speed unknown (dual-channel DDR4-3200 assumed)
  • mixture-of-experts: speed depends on expert routing

Other quantizations on the RTX 2080 Ti

gpt-oss-120b on RTX 2080 Ti + 64 GB RAM · 8K context
gpt-oss-120b MXFP48K~63.2 GB · No dataIncompatible

Alternatives

GPUs that run gpt-oss-120b MXFP4 entirely in VRAM

Other models that fit the RTX 2080 Ti

Hardware that runs gpt-oss-120b MXFP4 entirely in memory

Prices and links follow the market you choose.

Radeon PRO W7900

AMD

ExcellentRuns gpt-oss-120b MXFP4 entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

NVIDIA DGX Spark (GB10)

Unified memory PC

ExcellentRuns gpt-oss-120b MXFP4 entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the RTX 2080 Ti run gpt-oss-120b?
The model needs about 63.2 GB; VRAM plus usable RAM give 61.9 GB. 1.3 GB are missing.
Which quantization should I use on the RTX 2080 Ti?
None fits entirely in VRAM at 8K context; the smallest, MXFP4, still needs offload.
What is the largest context on the RTX 2080 Ti?
At MXFP4, the model does not fit entirely in VRAM even at a short context.