Written by Jakub Rusinowski · Last updated August 15, 2026
Technically yes, but not recommended
It loads, but it is not worth running — GPT-oss 120B at Q6_K fits in Framework Desktop (Ryzen AI Max+ 395, 128 GB)'s 128 GB, yet the memory bandwidth limits it to ~1.9 tok/s (estimated), well below usable interactive speed.
Confidence: high · Recommended quantization: Q6_K · Estimated speed: ~1.9 tok/s
| Usable memory for models | 128 GB |
| Memory bandwidth | 256 GB/s |
| Form factor | Mini PC |
| Operating system | Windows or Linux |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 241.4 GB | ✗ No | — | — | 240 GB |
| Q8_0 | 128.9 GB | ✗ No | — | — | 127.5 GB |
| Q6_K | 99.8 GB | ✓ Yes | 64K | ~1.9 tok/s | 98.4 GB |
| Q5_K_M | 86.5 GB | ✓ Yes | 64K | ~2.2 tok/s | 85.1 GB |
| Q4_K_M | 73.9 GB | ✓ Yes | 64K | ~2.6 tok/s | 72.5 GB |
| Q3_K_M | 52.6 GB | ✓ Yes | 64K | ~3.7 tok/s | 51.2 GB |
| Q2_K | 40.9 GB | ✓ Yes | 64K | ~4.8 tok/s | 39.4 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GPT-oss 120B | 73.9 GB | ✓ Fits | ~2.6 tok/s |
| GPT-OSS 20B | 13.3 GB | ✓ Fits | ~15.1 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
It loads, but it is not worth running — GPT-oss 120B at Q6_K fits in Framework Desktop (Ryzen AI Max+ 395, 128 GB)'s 128 GB, yet the memory bandwidth limits it to ~1.9 tok/s (estimated), well below usable interactive speed.
Q6_K — it needs about 99.8 GB of the 128 GB available, downloads as roughly 98.4 GB, and runs at an estimated 1.9 tokens/sec with up to 64K of context.
Memory bandwidth. The model fits, but at 256 GB/s it can only be read fast enough for roughly 1.9 tokens/sec.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving