Can I Run DeepSeek V4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated April 24, 2026

Yes, but it is tight

Yes, but it is tight — DeepSeek V4-Flash at Q3_K_M needs about 122.4 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving only ~5.6 GB before the runtime starts swapping. Expect ~30.7 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: low · Recommended quantization: Q3_K_M · Estimated speed: ~30.7 tok/s

Framework Desktop (Ryzen AI Max+ 395, 128 GB) — what it gives a model

Usable memory for models128 GB
Memory bandwidth256 GB/s
Form factorMini PC
Operating systemWindows or Linux
Memory upgradeableNo — soldered

DeepSeek V4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

QuantMemory neededFits 128 GB?Max contextEst. speedDownload
F16569.4 GB✗ No568 GB
Q8_0303.1 GB✗ No301.8 GB
Q6_K234.3 GB✗ No232.9 GB
Q5_K_M202.7 GB✗ No201.3 GB
Q4_K_M172.8 GB✗ No171.5 GB
Q3_K_M122.4 GB✓ Yes64K~30.7 tok/s121.1 GB
Q2_K94.7 GB✓ Yes256K~38.5 tok/s93.4 GB

Which DeepSeek V4 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
DeepSeek V4-Pro967.4 GB✗ Too large
DeepSeek V4-Flash172.8 GB✗ Too large

What to watch out for

Framework Desktop 128 GB limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

Can I run DeepSeek V4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, but it is tight — DeepSeek V4-Flash at Q3_K_M needs about 122.4 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving only ~5.6 GB before the runtime starts swapping. Expect ~30.7 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of DeepSeek V4 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q3_K_M — it needs about 122.4 GB of the 128 GB available, downloads as roughly 121.1 GB, and runs at an estimated 30.7 tokens/sec with up to 64K of context.

What limits DeepSeek V4 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 Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)

DeepSeek V4 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | DeepSeek V4 model page | Check your hardware