Can I Run MiniMax M2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Written by Jakub Rusinowski · Last updated February 15, 2026
Technically yes, but not recommended
It loads, but it is not worth running — MiniMax M2.5 230B at Q3_K_M fits in Framework Desktop (Ryzen AI Max+ 395, 128 GB)'s 128 GB, yet the memory bandwidth limits it to ~1.9 tok/s (estimated), well below usable interactive speed.
Confidence: medium · Recommended quantization: Q3_K_M · Estimated speed: ~1.9 tok/s
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 |
MiniMax M2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|
| F16 | 464.3 GB | ✗ No | — | — | 460 GB |
| Q8_0 | 248.7 GB | ✗ No | — | — | 244.4 GB |
| Q6_K | 192.9 GB | ✗ No | — | — | 188.6 GB |
| Q5_K_M | 167.3 GB | ✗ No | — | — | 163 GB |
| Q4_K_M | 143.2 GB | ✗ No | — | — | 138.9 GB |
| Q3_K_M | 102.4 GB | ✓ Yes | 64K | ~1.9 tok/s | 98 GB |
| Q2_K | 79.9 GB | ✓ Yes | 64K | ~2.5 tok/s | 75.6 GB |
What to watch out for
- At ~1.9 tok/s this loads but is too slow for interactive use — expect roughly 32 seconds per 60 tokens.
- Q3_K_M is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 1 larger variant of MiniMax M2.5 does not fit and would need CPU offload or different hardware.
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
- 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 inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run MiniMax M2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
It loads, but it is not worth running — MiniMax M2.5 230B at Q3_K_M fits in Framework Desktop (Ryzen AI Max+ 395, 128 GB)'s 128 GB, yet the memory bandwidth limits it to ~1.9 tok/s (estimated), well below usable interactive speed.
Which quantization of MiniMax M2.5 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q3_K_M — it needs about 102.4 GB of the 128 GB available, downloads as roughly 98 GB, and runs at an estimated 1.9 tokens/sec with up to 64K of context.
What limits MiniMax M2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Memory bandwidth. The model fits, but at 256 GB/s it can only be read fast enough for roughly 1.9 tokens/sec.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
MiniMax M2.5 on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | MiniMax M2.5 model page | Check your hardware