local intelligence

can it run

Can the Framework Desktop (192GB, PRO 495) run qwen3 1.7B?

YES

Comfortably. 192GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.

~110–160 tok/s

weights 1.4GB + KV cache 0.44GB at 4k context vs ~190GB usable → full. 1.8 GB needed of 190 GB usable — headroom for context

computed roofline: 256 GB/s × 0.60–0.85 efficiency window / 1.4GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).

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

Specs

model file1.4GB (GGUF Q4_K_M)
minimum memory4GB working set
this machine192GB LPDDR5X
params1.7B
licenseapache-2.0
price$4499

Run it

model files: hugging face ↗

easy run: ollama pull qwen3:1.7b

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

Alternatives

no alternatives — every machine in the catalog can run this one.

Buy

Framework ↗ · Amazon ↗

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