Written by Jakub Rusinowski · Last updated July 21, 2026
Yes — comfortably
Yes, comfortably — Cosmos 3 Super at Q8_0 needs about 71.1 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~56.9 GB spare and running at ~5.4 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~5.4 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 | 131.1 GB | ✗ No | — | — | 128 GB |
| Q8_0 | 71.1 GB | ✓ Yes | 16K | ~5.4 tok/s | 68 GB |
| Q6_K | 55.6 GB | ✓ Yes | 16K | ~6.9 tok/s | 52.5 GB |
| Q5_K_M | 48.5 GB | ✓ Yes | 16K | ~7.9 tok/s | 45.4 GB |
| Q4_K_M | 41.8 GB | ✓ Yes | 16K | ~9.2 tok/s | 38.6 GB |
| Q3_K_M | 30.4 GB | ✓ Yes | 16K | ~12.6 tok/s | 27.3 GB |
| Q2_K | 24.2 GB | ✓ Yes | 16K | ~15.9 tok/s | 21 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Cosmos 3 Super | 41.8 GB | ✓ Fits | ~9.2 tok/s |
| Cosmos 3 Nano | 11.9 GB | ✓ Fits | ~32.1 tok/s |
| Cosmos 3 Edge | 4.1 GB | ✓ Fits | ~91.8 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, comfortably — Cosmos 3 Super at Q8_0 needs about 71.1 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~56.9 GB spare and running at ~5.4 tok/s (estimated), with room for about 16,384 tokens of context.
Q8_0 — it needs about 71.1 GB of the 128 GB available, downloads as roughly 68 GB, and runs at an estimated 5.4 tokens/sec with up to 16K 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