local intelligence

can it run

Can the GTX 1080 Ti (11GB, used) run gpt-oss 20B MoE?

NO

No. 11GB of memory can't hold the 18GB working set this model needs. A smaller quant or a bigger machine is required.

~65–120 tok/s (active-expert estimate)

weights 14GB + KV cache 0.19GB at 4k context vs ~11GB usable → no. 14.2 GB vs 11 GB usable — does not fit

computed roofline: 484 GB/s × 0.28–0.50 efficiency window / 2.1GB (Q4_K_M) — bands, never points.

MoE: file is 14GB (that decides fit) but only ~3B of experts activate per token (~2.1GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

explore the full catalog84 machines indexed · live prices · what each one can run

Specs

model file14GB (GGUF Q4_K_M)
minimum memory18GB working set
this machine11GB GDDR5X, 484 GB/s
params20B MoE
licenseapache-2.0
price$275

Run it

model files: hugging face ↗

easy run: ollama pull gpt-oss:20b

runs with: ollama · llama.cpp · koboldcpp · lm studio

Alternatives

Mac mini M4 (32GB) — cheapest machine that runs it ($999)

every model the GTX 1080 Ti (11GB, used) can run — full list

RTX 3090 (24GB, used) — upgrade path machine

Buy

eBay (used) ↗ · Amazon ↗

2026-09-17 · ← all models on the GTX 1080 Ti (11GB, used) · ← full hardware catalog · prices verified at source, may drift