Sunk Cost sunkcost.ai Data checked 2026-09-03

Can a Strix Halo Framework Desktop, 192GB run local LLMs?

Yes — 36 of the 39 open models on this site fit in its 160 GB of usable memory, the strongest being Qwen3.8 Flash Next. Whether that saves you money is a different question, and the answer is usually no.

Pricenot published yet
Memory192 GB, about 160 GB of it addressable by the GPU at 273 GB/s
Best model it runsQwen3.8 Flash Next — Sonnet-class, 31 tok/s
Pay-back against the APIcannot be computed yet

Run the numbers on this machine

What it runs

ModelSpeedClassGood atMemory
Qwen3.8 Flash NextQ4_K_M 31 tok/s Sonnet-class 121 GB
DeepSeek V4-FlashUD-Q4_K_M 20 tok/s Sonnet-class 155 GB
Qwen3.8 27BQ4_K_M 11 tok/s Sonnet-class 19 GB
Ling 3.0 flashQ4_K_M 22 tok/s Haiku-class 82 GB
MiniMax M2.7Q4_K_M 10 tok/s Haiku-class 149 GB
Qwen3.6 27BQ4_K_M 11 tok/s Haiku-class 19 GB
Qwen3.6 35B-A3BQ4_K_M 60 tok/s Haiku-class 23 GB
Muse Glimmer 30BQ4_K_M 11 tok/s Haiku-class 18 GB
Gemma 4 26B-A4BQ4_K_M 44 tok/s Haiku-class 18 GB
Qwen3.5 122B-A10BUD-Q4_K_M 21 tok/s Haiku-class 79 GB
Gemma 4 31B itQ4_K_M 7.9 tok/s Haiku-class 26 GB
Granite 4.2 30BQ4_K_M 7.8 tok/s Haiku-class 26 GB

24 more fit; the calculator lists them all.

The specifics

Chip
Framework Desktop — Ryzen AI Max+ PRO 495 'Gorgon Halo' · 192 GB
Memory bandwidth
273 GB/s
Usable by the GPU
160 GB — 192 GB unified, of which AMD states 160 GB can be allocated to the GPU — the largest GPU-addressable pool of anything on this list under $10,000, if it ships at a sane price. Windows lets you dedicate up to 75% of RAM to the GPU (Variable Graphics Memory in AMD Adrenalin). On Linux the amdgpu GTT pool can be raised to roughly 108-120 GB with ttm.pages_limit / amdgpu.gttsize boot parameters. The Windows figure is used here as the conservative one. Measured GPU bandwidth is ~212-215 GB/s of the 256 GB/s theoretical, so estimates here run a little high.
Power under load
133 W (stand in) — No measurement for Gorgon Halo; stand-in is the Framework Desktop's measured 133 W on the previous chip.
Availability
Announced, not yet priced or orderable.
Sources
source 1