RTX 5060 Ti 8GB can't get to Llama 4 Scout 17B at any price. Here's what actually can.

Llama 4 Scout 17B at Q4_K_M needs 68.2 GB once weights, KV cache at 8K context and framework overhead are counted. RTX 5060 Ti 8GB offers 8 GB, leaving you 60.2 GB short. 128 GB of unified memory leaves about 96 GB for a model after the OS takes its share, which holds Llama 4 Scout 17B at Q4_K_M.

What to do

Move to Ryzen AI Max+ 395 mini PC, 128GB unified

128 GB of unified memory leaves about 96 GB for a model after the OS takes its share, which holds Llama 4 Scout 17B at Q4_K_M.

What it needs

Memory is fixed at purchase on these machines — choose the capacity you will still want in three years

What we checked

Unified memory: 128 GB, of which roughly 96 GB is usable by a model
Model requires 68.2 GB at Q4_K_M

Other ways to get there

Rent a GPU by the hour instead — You want this daily, so renting is the way to try Llama 4 Scout 17B before spending on hardware — not the long-run answer if the usage holds.
Consider waiting this market out — DDR5 kit prices are roughly 3-4x their mid-2025 level, and the shortage is expected to run into 2027. Relief is not expected before 2027-Q4. Meanwhile you have a way to run this that costs nothing extra.

What we ruled out, and why

96GB DDR5 kit (2x48GB) — More memory would let this model load, but the parts of it living in system RAM have to travel over PCIe, so it would run at roughly 2.1-4.4 tok/s — slower than reading speed. More VRAM, not more RAM, is what this needs.
128GB DDR5 kit (4x32GB) — More memory would let this model load, but the parts of it living in system RAM have to travel over PCIe, so it would run at roughly 2.1-4.4 tok/s — slower than reading speed. More VRAM, not more RAM, is what this needs.

Market conditions: DDR5 kit prices are roughly 3-4x their mid-2025 level, and the shortage is expected to run into 2027. Relief is not expected before 2027-Q4. Source, checked 2026-08-26.

Check current price

Ryzen AI Max+ 395 mini PC, 128GB unified — 128 GB unified memory

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Your machine is not exactly this one. Run this for your exact setup — the form opens pre-filled with RTX 5060 Ti 8GB and Llama 4 Scout 17B.

Questions people ask about this pairing

Can an RTX 5060 Ti 8GB run Llama 4 Scout 17B?

Not as it stands. Llama 4 Scout 17B needs 68.2 GB at Q4_K_M and this machine has 8 GB available, a shortfall of 60.2 GB. 128 GB of unified memory leaves about 96 GB for a model after the OS takes its share, which holds Llama 4 Scout 17B at Q4_K_M.

Would more system RAM fix this?

More memory would let this model load, but the parts of it living in system RAM have to travel over PCIe, so it would run at roughly 2.1-4.4 tok/s — slower than reading speed. More VRAM, not more RAM, is what this needs.

Should I wait for prices to come down?

DDR5 kit prices are roughly 3-4x their mid-2025 level, and the shortage is expected to run into 2027. Relief is not expected before 2027-Q4. The current estimate for relief is 2027-Q4. If you can run this some other way meanwhile, waiting is defensible; if you cannot, the part still does the job today.

Does a longer context change what Llama 4 Scout 17B needs here?

Yes, and it is the figure people forget. The 68.2 GB above already includes the KV cache at 8K; that cache grows roughly linearly with context, so doubling the window adds real gigabytes rather than a rounding error. If you plan to work with long documents on RTX 5060 Ti 8GB, size for the context you will actually use, not the default.

Data behind this page last checked 2026-08-26.