Written by Jakub Rusinowski · Last updated August 15, 2026
Yes — comfortably
Yes, comfortably — Granite 4.0 Small-H 32B-A9B at Q8_0 needs about 36.6 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~91.4 GB spare and running at ~17.6 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~17.6 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 | 66.6 GB | ✓ Yes | 128K | ~9.9 tok/s | 64 GB |
| Q8_0 | 36.6 GB | ✓ Yes | 128K | ~17.6 tok/s | 34 GB |
| Q6_K | 28.9 GB | ✓ Yes | 128K | ~22 tok/s | 26.2 GB |
| Q5_K_M | 25.3 GB | ✓ Yes | 128K | ~24.8 tok/s | 22.7 GB |
| Q4_K_M | 22 GB | ✓ Yes | 128K | ~28.3 tok/s | 19.3 GB |
| Q3_K_M | 16.3 GB | ✓ Yes | 128K | ~37 tok/s | 13.6 GB |
| Q2_K | 13.2 GB | ✓ Yes | 128K | ~44.5 tok/s | 10.5 GB |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, comfortably — Granite 4.0 Small-H 32B-A9B at Q8_0 needs about 36.6 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~91.4 GB spare and running at ~17.6 tok/s (estimated), with room for about 131,072 tokens of context.
Q8_0 — it needs about 36.6 GB of the 128 GB available, downloads as roughly 34 GB, and runs at an estimated 17.6 tokens/sec with up to 128K 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
← Can I Run It? | IBM Granite 4.0 model page | Check your hardware