Can I Run Aya Expanse on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Written by Jakub Rusinowski · Last updated October 8, 2024
Yes — comfortably
Yes, comfortably — Aya Expanse 32B at Q8_0 needs about 36.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~91.5 GB spare and running at ~5.4 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~5.4 tok/s
See what else this hardware can run →
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
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 |
Aya Expanse on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 66.7 GB | ✓ Yes | 64K | ~2.9 tok/s | 64.6 GB |
| Q8_0 | 36.5 GB | ✓ Yes | 64K | ~5.4 tok/s | 34.3 GB |
| Q6_K | 28.6 GB | ✓ Yes | 64K | ~7 tok/s | 26.5 GB |
| Q5_K_M | 25 GB | ✓ Yes | 64K | ~8 tok/s | 22.9 GB |
| Q4_K_M | 21.6 GB | ✓ Yes | 64K | ~9.3 tok/s | 19.5 GB |
| Q3_K_M | 15.9 GB | ✓ Yes | 64K | ~12.9 tok/s | 13.8 GB |
| Q2_K | 12.8 GB | ✓ Yes | 64K | ~16.4 tok/s | 10.6 GB |
Which Aya Expanse sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Aya Expanse 32B | 21.6 GB | ✓ Fits | ~9.3 tok/s |
| Aya Expanse 8B | 6.7 GB | ✓ Fits | ~33 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 Aya Expanse on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes, comfortably — Aya Expanse 32B at Q8_0 needs about 36.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~91.5 GB spare and running at ~5.4 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Aya Expanse should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q8_0 — it needs about 36.5 GB of the 128 GB available, downloads as roughly 34.3 GB, and runs at an estimated 5.4 tokens/sec with up to 64K of context.
What limits Aya Expanse 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)
- BitNet b1.58 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Bonsai 27B on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Codestral on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Cogito v1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Command R Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
Aya Expanse on GPUs
- Aya Expanse on NVIDIA GeForce RTX 5090
- Aya Expanse on NVIDIA GeForce RTX 5070
- Aya Expanse on NVIDIA GeForce RTX 5060 Ti 8GB
- Aya Expanse on NVIDIA GeForce RTX 5060
What This Model Is Good At
- Best local LLMs for document analysis
- Best local LLMs for translation
- Best local LLMs for enterprise assistant
Model & Tools
← Can I Run It? | Aya Expanse model page | Check your hardware