the AI bench
VERIFIED AUGUST 2026
All hardware

HARDWARE · MoE MINI-PC · 128 GB UNIFIED

Framework Desktop (Ryzen AI Max+ 395)

The first mini-PC with GPU-class bandwidth and 128 GB unified memory.

Strix Halo's 40-CU Radeon 8060S iGPU plus 128 GB LPDDR5X unified memory runs Qwen 3 30B-A3B MoE at ~72 tok/s — 4× the bandwidth of the Minisforum UM890 Pro, 4× the memory. A genuine local-AI mini-PC, not a CPU box that happens to boot.

The decision in five lines

The call
Buy — The first mini-PC with GPU-class bandwidth and 128 GB unified memory.
Best for
MoE mini-PC
Runs well
Qwen3-Coder-30B-A3B (MoE, fits 24GB) · Qwen 3.5 35B-A3B (MoE, fits 24GB) · Gemma 4 31B (256K context)
Watch out
Backend choice is load-bearing. Vulkan (RADV) beats ROCm/HIP for MoE token generation on the same hardware; HIP hits ~40% of theoretical throughput per llama.cpp #13565. Best practice varies per model family — check recent benchmark threads before assuming either backend wins everywhere.
Evidence
Estimated · last verified August 2026

128
GB UNIFIED
~212
GB/S MEASURED
45–120
W CONFIGURABLE
$3,449
128 GB (AUG 2026)

What fits at this tier

128 GB LPDDR5X unified with up to 96 GB assignable as VRAM to the 8060S iGPU. Llama 3.1 8B Q4 at ~42 tok/s (Vulkan). Qwen 3 30B-A3B MoE Q4 at ~72 tok/s (the story pick — MoE-on-unified-memory unlock). Llama 4 Scout 109B MoE Q4 at ~20 tok/s. 70B dense Q4 technically fits but runs at ~5 tok/s — a demo, not a daily driver.

CODING
Qwen3-Coder-30B-A3B (MoE, fits 24GB) 3B-active MoE — benchmark champion for local coding at this tier.
CHAT / GENERAL
Qwen 3.5 35B-A3B (MoE, fits 24GB) 3B active MoE — 30B quality at 3B inference speed.
DOCS & RETRIEVAL
Gemma 4 31B (256K context) 31B dense with 256K context; Gemma commercial-permissive terms; Arena top 5.
IMAGE
HiDream-O1-Image (8B, MIT) May 8, 2026 release. Pixel-space (no VAE, no disjoint text encoder) — debuted top-10 on Artificial Analysis T2I Arena. MIT-licensed 8B; one model handles T2I + edit + subject-driven personalization at up to 2,048².
AGENTS
Qwen 3.5 35B-A3B (MoE, fits 24GB) MoE with native tool use; fits 24GB at Q4; Apache 2.0.
VOICE
VoxCPM2 (2B, Apache 2.0) 30 languages, 48 kHz, tokenizer-free diffusion AR; voice design from text. April 2026 release.

The call

Buy it if your work is MoE-heavy (Qwen 3.5 35B-A3B, Llama 4 Scout) and you want a small quiet box instead of a GPU tower. Framework's repair ethos + mini-ITX upgrade path is the premium over competing Strix Halo SKUs from GMKtec / Beelink / HP.

Skip it if you want dense 70B at interactive speed — that's not this box, despite what the 128 GB number suggests. Also skip if you need a warranty-backed workstation — go HP Z2 Mini G1a (~$3,734) for enterprise warranty coverage.

Watchouts

  • Backend choice is load-bearing. Vulkan (RADV) beats ROCm/HIP for MoE token generation on the same hardware; HIP hits ~40% of theoretical throughput per llama.cpp #13565. Best practice varies per model family — check recent benchmark threads before assuming either backend wins everywhere.
  • 70B dense is a trap. 128 GB fits it, but 5 tok/s makes it unusable for interactive work. Treat this as a MoE specialist, not a 70B dense machine.
  • The price is a moving target, and it only moves up. The 128 GB config launched at $1,999 (Feb 2025), hit $2,459 in January 2026, and is $3,449 as of August 2026 — a 73% rise driven entirely by LPDDR5X, which Framework documents update-by-update on its own pricing blog (increases landed in Jan, Feb, Mar, Apr, May, Jun and twice in Jul). Budget for another rise rather than a cut: DRAM contract prices rose 58–63% in Q2 2026 and analysts now push relief out past 2027. The cheap-alternative escape hatch has closed too — GMKtec's EVO-X2 128 GB was ~$1,500 earlier this year and is now $3,399–$3,499, and Micro Center's AMD Ryzen AI Halo box is $3,999. Framework is no longer paying a repairability premium; it is simply the market price for 128 GB of unified memory.
  • Supply chain: 128 GB batches keep selling out. Plan on 1–6 week wait even when Framework's store shows "in stock."
  • The 50 TOPS XDNA 2 NPU is largely unused by llama.cpp / Ollama / LM Studio as of July 2026. Don't buy for NPU — the bandwidth + 128 GB unified is the actual value.

Local vs cloud at this tier

● LOCAL WINS

MoE 30B-A3B and 109B-A17B unbounded at interactive speeds in a 4.5 L box, at a fraction of the wattage of a GPU tower.

● CLOUD WINS

Cloud wins on dense 70B+ (Mac Studio M3 Ultra 96 GB is the local path there, not this), frontier reasoning, first-day model access.

Fills a real gap between 24 GB NVIDIA cards and Mac Studio Ultra: if your workload is MoE-shaped (which is where the frontier is trending), this is the most useful mini-PC ever shipped. If your workload is 70B dense, look elsewhere.

Next step

Load this setup into the planner