Can I Run InternLM 3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated January 15, 2025

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

InternLM 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	42.4 GB	✓ Yes	32K	~4.7 tok/s	40 GB
Q8_0	23.6 GB	✓ Yes	32K	~8.5 tok/s	21.3 GB
Q6_K	18.8 GB	✓ Yes	32K	~10.9 tok/s	16.4 GB
Q5_K_M	16.6 GB	✓ Yes	32K	~12.5 tok/s	14.2 GB
Q4_K_M	14.5 GB	✓ Yes	32K	~14.4 tok/s	12.1 GB
Q3_K_M	10.9 GB	✓ Yes	32K	~19.7 tok/s	8.5 GB
Q2_K	9 GB	✓ Yes	32K	~24.6 tok/s	6.6 GB

Which InternLM 3 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
InternLM 3 20B Instruct	14.5 GB	✓ Fits	~14.4 tok/s
InternLM 3 8B Instruct	6.5 GB	✓ Fits	~32.3 tok/s

What to watch out for

• 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 InternLM 3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, comfortably — InternLM 3 20B Instruct at Q8_0 needs about 23.6 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~104.4 GB spare and running at ~8.5 tok/s (estimated), with room for about 32,768 tokens of context.

Which quantization of InternLM 3 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q8_0 — it needs about 23.6 GB of the 128 GB available, downloads as roughly 21.3 GB, and runs at an estimated 8.5 tokens/sec with up to 32K of context.

What limits InternLM 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

• InternLM 3 on Mac mini M4 16 GB
• InternLM 3 on Mac mini M4 Pro 64 GB
• InternLM 3 on Beelink SER9 32 GB

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)

InternLM 3 on GPUs

• InternLM 3 on NVIDIA GeForce RTX 5080
• InternLM 3 on NVIDIA GeForce RTX 5070 Ti
• InternLM 3 on NVIDIA GeForce RTX 5070
• InternLM 3 on NVIDIA GeForce RTX 5060 Ti 16GB

What This Model Is Good At

• Best local LLMs for reasoning
• Best local LLMs for rag
• Best local LLMs for research

Model & Tools

• InternLM 3 model page
• VRAM calculator
• Check your own hardware

← Can I Run It? | InternLM 3 model page | Check your hardware