Can I Run Qwen 3.6 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 22 kwietnia 2026
Yes — comfortably
Yes, comfortably — Qwen 3.6 35B-A3B at Q8_0 needs about 38.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~89.8 GB spare and running at ~50.9 tok/s (estimated), with room for about 262,144 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~50.9 tok/s
See what else this hardware can run →
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
Framework Desktop (Ryzen AI Max+ 395, 128 GB) — what it gives a model
| Usable memory for models | 128 GB |
| Memory bandwidth | 256 GB/s |
| Form factor | Mini PC |
| Operating system | Windows or Linux |
| Memory upgradeable | No — soldered |
Qwen 3.6 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 71 GB | ✓ Yes | 256K | ~29.2 tok/s | 70 GB |
| Q8_0 | 38.2 GB | ✓ Yes | 256K | ~50.9 tok/s | 37.2 GB |
| Q6_K | 29.7 GB | ✓ Yes | 256K | ~63.1 tok/s | 28.7 GB |
| Q5_K_M | 25.8 GB | ✓ Yes | 256K | ~70.9 tok/s | 24.8 GB |
| Q4_K_M | 22.2 GB | ✓ Yes | 256K | ~80.3 tok/s | 21.1 GB |
| Q3_K_M | 16 GB | ✓ Yes | 256K | ~103.2 tok/s | 14.9 GB |
| Q2_K | 12.5 GB | ✓ Yes | 256K | ~122.5 tok/s | 11.5 GB |
Which Qwen 3.6 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen 3.6 35B-A3B | 22.2 GB | ✓ Fits | ~80.3 tok/s |
| Qwen 3.6 27B | 18.3 GB | ✓ Fits | ~10.9 tok/s |
What to watch out for
- Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.
Framework Desktop 128 GB limitations
- Memory is soldered LPDDR5X — unusually for Framework, this is the one component that cannot be upgraded.
- ROCm/Vulkan support for Strix Halo is younger than CUDA; check your runtime supports it before buying.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 128 GB unified memory at 256 GB/s, shared between CPU and GPU.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Qwen 3.6 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes, comfortably — Qwen 3.6 35B-A3B at Q8_0 needs about 38.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~89.8 GB spare and running at ~50.9 tok/s (estimated), with room for about 262,144 tokens of context.
Which quantization of Qwen 3.6 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q8_0 — it needs about 38.2 GB of the 128 GB available, downloads as roughly 37.2 GB, and runs at an estimated 50.9 tokens/sec with up to 256K of context.
What limits Qwen 3.6 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Qwen3.8 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Qwen3-Coder on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- SmolLM2 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- SmolLM3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- StarCoder 2 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
Qwen 3.6 on GPUs
- Qwen 3.6 on NVIDIA GeForce RTX 5090
- Qwen 3.6 on NVIDIA GeForce RTX 5080
- Qwen 3.6 on NVIDIA GeForce RTX 5070 Ti
- Qwen 3.6 on NVIDIA GeForce RTX 5070