Spec overview, not a review. We have not tested this machine hands-on. Everything below is from the maker's published specs or dated retail listings. Performance results: TBD until we test it.
| System | Chip | Memory | Memory bandwidth | Price | Source |
|---|---|---|---|---|---|
| Framework Desktop (128GB, Ryzen AI Max+ 395) | AMD Ryzen AI Max+ 395 | 128 GB unified | 256 GB/s (computed: 256-bit × 8000 MT/s) | TBD Framework now also offers a Ryzen AI Max+ PRO 495 with up to 192GB. Prices not shown on the page we fetched: TBD. | Framework: Framework Desktop; AMD: Ryzen AI Max+ 395 specifications |
What it can run (estimates)
| Model | Params (total / active) | Est. memory, Q4 @ 8k ctx | Est. memory, Q8 @ 8k ctx | Cheapest fit in our data (Q4) |
|---|---|---|---|---|
| Qwen3 32B | 32.8B / 32.8B | 22.5 GB | 37.3 GB | GeForce RTX 3090 ($1,499, GPU launch MSRP) |
| Qwen3 30B-A3B (MoE) | 30.5B / 3.3B | 21.1 GB | 34.9 GB | GeForce RTX 3090 ($1,499, GPU launch MSRP) |
| Llama 3.3 70B | 70.6B / 70.6B | 46.8 GB | 78.7 GB | GMKtec EVO-X2 (128GB / 1TB) ($3,499.99, system, listed price) |
| gpt-oss-120b (MoE) | 117B / 5.1B | 64.7 GB | 126.8 GB | GMKtec EVO-X2 (128GB / 1TB) ($3,499.99, system, listed price) |
Parameter counts: Hugging Face: openai/gpt-oss-120b model card; Hugging Face: meta-llama/Llama-3.3-70B-Instruct; Hugging Face: Qwen3 model cards (e.g. Qwen/Qwen3-30B-A3B). Memory figures are our estimates (see methodology), not measurements.
Not listed here: noise, thermals, sustained performance, build quality: TBD until hands-on testing.
Compare: 128GB Strix Halo mini PCs.