Can I Run Falcon 3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Written by Jakub Rusinowski · Last updated December 18, 2024
Yes — comfortably
Yes, comfortably — Falcon 3 10B Instruct at Q8_0 needs about 13.1 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~114.9 GB spare and running at ~15.9 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~15.9 tok/s
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
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 |
Falcon 3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 22.7 GB | ✓ Yes | 32K | ~8.8 tok/s | 20.6 GB |
| Q8_0 | 13.1 GB | ✓ Yes | 32K | ~15.9 tok/s | 10.9 GB |
| Q6_K | 10.6 GB | ✓ Yes | 32K | ~20.1 tok/s | 8.4 GB |
| Q5_K_M | 9.4 GB | ✓ Yes | 32K | ~22.9 tok/s | 7.3 GB |
| Q4_K_M | 8.4 GB | ✓ Yes | 32K | ~26.2 tok/s | 6.2 GB |
| Q3_K_M | 6.5 GB | ✓ Yes | 32K | ~35 tok/s | 4.4 GB |
| Q2_K | 5.5 GB | ✓ Yes | 32K | ~42.8 tok/s | 3.4 GB |
Which Falcon 3 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Falcon 3 10B Instruct | 8.4 GB | ✓ Fits | ~26.2 tok/s |
| Falcon 3 7B Instruct | 6.2 GB | ✓ Fits | ~35.5 tok/s |
| Falcon 3 3B Instruct | 3.5 GB | ✓ Fits | ~69.8 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 Falcon 3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes, comfortably — Falcon 3 10B Instruct at Q8_0 needs about 13.1 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~114.9 GB spare and running at ~15.9 tok/s (estimated), with room for about 32,768 tokens of context.
Which quantization of Falcon 3 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q8_0 — it needs about 13.1 GB of the 128 GB available, downloads as roughly 10.9 GB, and runs at an estimated 15.9 tokens/sec with up to 32K of context.
What limits Falcon 3 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)
- Gemma 2 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Gemma 3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Gemma 3n on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Gemma 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- GLM-4.7 / GLM-Z1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
Falcon 3 on GPUs
- Falcon 3 on NVIDIA GeForce RTX 5070
- Falcon 3 on NVIDIA GeForce RTX 5060 Ti 8GB
- Falcon 3 on NVIDIA GeForce RTX 5060
- Falcon 3 on NVIDIA GeForce RTX 4070 Ti
What This Model Is Good At
- Best local LLMs for general assistant
- Best local LLMs for writing
- Best local LLMs for document analysis