Written by Jakub Rusinowski · Last updated July 15, 2026
Yes — comfortably
Yes, comfortably — 1-bit Bonsai 27B at Q8_0 needs about 31.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~96.8 GB spare and running at ~6.4 tok/s (estimated), with room for about 262,144 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~6.4 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 | 56.5 GB | ✓ Yes | 256K | ~3.5 tok/s | 54 GB |
| Q8_0 | 31.2 GB | ✓ Yes | 256K | ~6.4 tok/s | 28.7 GB |
| Q6_K | 24.7 GB | ✓ Yes | 256K | ~8.2 tok/s | 22.1 GB |
| Q5_K_M | 21.7 GB | ✓ Yes | 256K | ~9.4 tok/s | 19.1 GB |
| Q4_K_M | 18.8 GB | ✓ Yes | 256K | ~10.9 tok/s | 16.3 GB |
| Q3_K_M | 14.1 GB | ✓ Yes | 256K | ~15 tok/s | 11.5 GB |
| Q2_K | 11.4 GB | ✓ Yes | 256K | ~18.9 tok/s | 8.9 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| 1-bit Bonsai 27B | 18.8 GB | ✓ Fits | ~10.9 tok/s |
| Ternary Bonsai 27B | 18.8 GB | ✓ Fits | ~10.9 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, comfortably — 1-bit Bonsai 27B at Q8_0 needs about 31.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~96.8 GB spare and running at ~6.4 tok/s (estimated), with room for about 262,144 tokens of context.
Q8_0 — it needs about 31.2 GB of the 128 GB available, downloads as roughly 28.7 GB, and runs at an estimated 6.4 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
← Can I Run It? | Bonsai 27B model page | Check your hardware