local intelligence

can it run

Can the Jetson Orin Nano Super dev kit run mixtral 8x7B MoE?

NO

No. 8GB of memory can't hold the 33GB working set this model needs. A smaller quant or a bigger machine is required.

~4.4–11 tok/s (active-expert estimate)

weights 26GB + KV cache 0.5GB at 4k context vs ~6GB usable → no. 26.5 GB vs 6 GB usable — does not fit

computed roofline: 68 GB/s × 0.25–0.65 efficiency window / 3.9GB (Q4_K_M) — bands, never points.

MoE: file is 26GB (that decides fit) but only ~1.05B of experts activate per token (~3.9GB 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 file26GB (GGUF Q4_K_M)
minimum memory33GB working set
this machine8GB unified
params8x7B MoE
licenseapache-2.0
price$499

Run it

model files: hugging face ↗

easy run: ollama pull mixtral:8x7b

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

Alternatives

Mac mini M5 Pro (64GB) — cheapest machine that runs it ($1669)

every model the Jetson Orin Nano Super dev kit can run — full list

Buy

NVIDIA (direct) ↗ · Amazon ↗

2026-09-17 · ← all models on the Jetson Orin Nano Super dev kit · ← full hardware catalog · prices verified at source, may drift