Framework Desktop (Ryzen AI Max+ 395, 128GB)
$3,449
The cheapest credible 128GB box and the best one for tinkerers. Framework drops the Ryzen AI Max+ 395 onto a standard mini-ITX mainboard (it fits any ITX case), with open firmware and the repairability Framework is known for — though, like every Strix Halo box, the memory itself is soldered. Direct-only: no Amazon, so we link to Framework.
Affiliate links — We earn a commission on qualifying purchases at no cost to you.
Specifications
| APU | AMD Ryzen AI Max+ 395 (16C/32T, Zen 5) |
| GPU | Radeon 8060S (40 CU, RDNA 3.5) |
| NPU | 50 TOPS (XDNA 2) |
| Unified Memory | 128GB LPDDR5X-8000 (up to 96GB GPU-allocatable) |
| Memory Bandwidth | 256 GB/s theoretical (~215 GB/s real) |
| Storage | Dual M.2 NVMe |
| Form Factor | 4.5L mini-ITX (standard board), Noctua cooler |
| I/O | USB4, 2× front expansion bays |
Pros
- Cheapest credible 128GB box ($1,999)
- Standard mini-ITX mainboard + open firmware — best Linux/tinkerer story
- Framework repairability + customizable expansion tiles
Cons
- Direct-only — not on Amazon
- Soldered RAM (modularity doesn't extend to memory)
- iGPU ~RTX 4070-mobile class — not a discrete-GPU replacement
Related Articles
DGX Spark 64GB vs Strix Halo 128GB: NVIDIA's $4,999 Spark Has Half the Memory — Should You Buy It?
On October 2 NVIDIA launched a 64GB DGX Spark at $4,999 and moved the 128GB Spark to $6,950. Every 128GB Strix Halo box in our catalog costs less than the new entry Spark. Here's the price-per-GB math, what actually fits in 64GB, and who should still pay for CUDA.
Mac Studio M5 Max vs Strix Halo: What Apple's September 2026 Refresh Changes for Local LLMs
Apple's M5 Max hits 614 GB/s — roughly 2.9× a Strix Halo box. But the $2,499 headline is a 36GB machine, and getting to 128GB runs a +$600 / +$400 / +$2,000 memory ladder. Here's the arithmetic, including the half that says buy the Mac.
RTX Spark vs Strix Halo: Buy a 128GB Box Now, or Wait for NVIDIA's October Launch?
NVIDIA's RTX Spark (N1X) ships in October with up to 128GB of unified memory — and NVIDIA's own porting guide puts it at 300 GB/s, not the 600 GB/s everyone is quoting. Here's what that actually changes about the box you buy this week.
How Much Context Can a 128GB Mini PC Actually Hold? The KV Cache Math Nobody Runs Before Buying
Everyone sizes a unified-memory box against model weights. Almost nobody sizes it against the KV cache — and on a 128K-token agent run, the cache is the number that decides whether the job finishes. Here's the math, box by box, plus the KV-quantization trade that makes long first prompts slower, not faster.
Related Products
Disclosure: Some links on this page are affiliate links. We may earn a commission if you make a purchase — at no extra cost to you. This helps support our independent reviews.