Written by Jakub Rusinowski · Last updated April 22, 2026
Yes — comfortably
Yes, comfortably — Qwen 3.6 35B-A3B at Q8_0 needs about 39.9 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~88.1 GB spare and running at ~42.1 tok/s (estimated), with room for about 262,144 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~42.1 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 | 72.7 GB | ✓ Yes | 128K | ~26 tok/s | 70 GB |
| Q8_0 | 39.9 GB | ✓ Yes | 256K | ~42.1 tok/s | 37.2 GB |
| Q6_K | 31.4 GB | ✓ Yes | 256K | ~50.1 tok/s | 28.7 GB |
| Q5_K_M | 27.5 GB | ✓ Yes | 256K | ~54.9 tok/s | 24.8 GB |
| Q4_K_M | 23.8 GB | ✓ Yes | 256K | ~60.3 tok/s | 21.1 GB |
| Q3_K_M | 17.6 GB | ✓ Yes | 256K | ~72.5 tok/s | 14.9 GB |
| Q2_K | 14.2 GB | ✓ Yes | 256K | ~81.5 tok/s | 11.5 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen 3.6 35B-A3B | 23.8 GB | ✓ Fits | ~60.3 tok/s |
| Qwen 3.6 27B | 19.3 GB | ✓ Fits | ~10.6 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, comfortably — Qwen 3.6 35B-A3B at Q8_0 needs about 39.9 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~88.1 GB spare and running at ~42.1 tok/s (estimated), with room for about 262,144 tokens of context.
Q8_0 — it needs about 39.9 GB of the 128 GB available, downloads as roughly 37.2 GB, and runs at an estimated 42.1 tokens/sec with up to 256K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving