Can I Run LFM2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Written by Jakub Rusinowski · Last updated October 15, 2026
Yes — comfortably
Yes, comfortably — LFM2.5-24B-A2B at Q8_0 needs about 26.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~101.5 GB spare and running at ~61.6 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~61.6 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 |
LFM2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 48.9 GB | ✓ Yes | 128K | ~35.5 tok/s | 48 GB |
| Q8_0 | 26.5 GB | ✓ Yes | 128K | ~61.6 tok/s | 25.5 GB |
| Q6_K | 20.7 GB | ✓ Yes | 128K | ~76.1 tok/s | 19.7 GB |
| Q5_K_M | 18 GB | ✓ Yes | 128K | ~85.3 tok/s | 17 GB |
| Q4_K_M | 15.5 GB | ✓ Yes | 128K | ~96.3 tok/s | 14.5 GB |
| Q3_K_M | 11.2 GB | ✓ Yes | 128K | ~123.1 tok/s | 10.2 GB |
| Q2_K | 8.8 GB | ✓ Yes | 128K | ~145.4 tok/s | 7.9 GB |
Which LFM2.5 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| LFM2.5-24B-A2B | 15.5 GB | ✓ Fits | ~96.3 tok/s |
| LFM2.5-8B-A1B | 7 GB | ✓ Fits | ~99.8 tok/s |
| LFM2.5 2.6B | 3.2 GB | ✓ Fits | ~78.1 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 LFM2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes, comfortably — LFM2.5-24B-A2B at Q8_0 needs about 26.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~101.5 GB spare and running at ~61.6 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of LFM2.5 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q8_0 — it needs about 26.5 GB of the 128 GB available, downloads as roughly 25.5 GB, and runs at an estimated 61.6 tokens/sec with up to 128K of context.
What limits LFM2.5 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)
- Llama 3.1 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Llama 3.2 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Llama 3.2 Vision on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Llama 3.3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Llama 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
LFM2.5 on GPUs
- LFM2.5 on NVIDIA GeForce RTX 5070
- LFM2.5 on NVIDIA GeForce RTX 5060 Ti 8GB
- LFM2.5 on NVIDIA GeForce RTX 5060
- LFM2.5 on NVIDIA GeForce RTX 4070 Ti