Can a Ryzen AI Max+ 395 128GB run DeepSeek V4 Flash 0731?
No
Only barely. It loads at IQ2_XXS, which compresses the weights far enough to visibly degrade the model, so the honest answer is that this pairing does not work.
The numbers
DeepSeek V4 Flash 0731 has 304.18 billion parameters across 43 layers, of which 20.36 billion are read for each token. The Ryzen AI Max+ 395 128GB has 128 GB of unified memory at 256 GB/s, of which about 96 GB is left for a model once the operating system has taken its share.
| Quantisation | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 301.86 GB | no | — |
| Q6_K | 233.16 GB | no | — |
| Q5_K_M | 202.35 GB | no | — |
| Q4_K_M | 171.9 GB | no | — |
| IQ4_XS | 151.36 GB | no | — |
| Q3_K_M | 139.32 GB | no | — |
| IQ3_XXS degraded | 109.22 GB | no | — |
| Q2_K degraded | 119.49 GB | no | — |
| IQ2_XXS degraded | 73.81 GB | yes | 34 t/s |
1 of the 9 levels fit. Levels marked degraded are listed for completeness, not as advice.
What to do instead
The straightforward answer is a smaller model from the same family. These do fit on a Ryzen AI Max+ 395 128GB, at a quantisation worth using:
- DeepSeek V4 Flash DSpark — 165.27B at Q4_K_M, 93.79 GB, about 14.5 tokens/s
- DeepSeek V4 Flash 0731 Spark — 60.31B at Q6_K, 46.92 GB, about 10.7 tokens/s
- DeepSeek Coder V2 Lite Instruct — 15.71B at Q8_0, 16.51 GB, about 56.4 tokens/s
Shortening the context window will not rescue this one: at 4k it still wants 171.77 GB against 171.9 GB at 8k, because the weights rather than the cache are what fill the card. The gap here is too large for settings to close.
Or the hardware that does run it
The cheapest device we track that runs DeepSeek V4 Flash 0731 at a quantisation worth using is the Apple M3 Ultra 256GB, around $5,599 for the whole machine, running it at Q4_K_M at about 55.8 tokens per second. Check the current price (affiliate link; indicative price reviewed 2026-09-01). Compare every option.
See how fast it feels
Ryzen AI Max+ 395 128GB running DeepSeek V4 Flash 0731 at IQ2_XXS
YouWhy does my model use more memory when the conversation gets longer?
Because of the KV cache. Every token you send leaves behind a key and a value vector in each layer of the model, and those stay in memory for as long as the conversation lasts.
The weights are a fixed cost: load a 4-bit 8B model and that is about 4.8 GB, whether you write one word or ten thousand. The cache is the part that grows, and it grows in a straight line with the number of tokens in the window.
How steeply depends on the model's attention design. With grouped-query attention, several query heads share one key-value pair, which cuts the cache by that ratio. Without it, every head keeps its own, and a long context can cost more memory than the weights themselves.
If you are short on memory, the first thing to try is lowering the context window in your runtime, not the quantisation.
Reading your question
Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.
Keep going
Everything the Ryzen AI Max+ 395 128GB runs, the full breakdown for DeepSeek V4 Flash 0731, or check a different pairing in the calculator.