local intelligence

can it run

Can the RTX 3090 (24GB, used) run gpt-oss 120B MoE?

NO

No. 24GB of memory can't hold the 82GB working set this model needs. A smaller quant or a bigger machine is required.

~44–73 tok/s (active-expert estimate)

weights 65GB + KV cache 0.28GB at 4k context vs ~24GB usable → no. 65.3 GB vs 24 GB usable — does not fit

computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 9.8GB (Q4_K_M) — bands, never points.

MoE: file is 65GB (that decides fit) but only ~18B of experts activate per token (~9.8GB 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 file65GB (GGUF Q4_K_M)
minimum memory82GB working set
this machine24GB GDDR6X, 936 GB/s
params120B MoE
licenseapache-2.0
price$1100

Run it

model files: hugging face ↗

easy run: ollama pull gpt-oss:120b

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

Alternatives

NIMO AI Mini PC (128GB) — cheapest machine that runs it ($1999)

rtx-5090 — the next step up from this machine's GPU

Buy

NVIDIA (used market) ↗ · Amazon ↗

2026-09-17 · ← full hardware catalog · prices verified at source, may drift