Home›Hardware›PC with Ryzen AI Max+ PRO 495 and 192 GB unified

Hardware sheet

PC with Ryzen AI Max+ PRO 495 and 192 GB unified

AMD chip with unified memory192 GiB273 GB/s15.4 TFLOPS

GMKtec EVO-X5 Pro, one of the PCs with this chip
GMKtec EVO-X5 Pro, one of the PCs with this chip Photo: GMKtec
ACEMAGIC F9A, another PC with this chip
ACEMAGIC F9A, another PC with this chip Photo: ACEMAGIC

Watch 2 videos

Once the system takes its share, this machine leaves 160.00 GiB for the model: room for 25 of the 28 models we measure at the reference compression, and the heaviest one that fits is deepseek-v4-flash. And how fast does it answer? That’s not down to the chip, but to its 273 GB/s of memory bandwidth.

At a glanceMachine data · 2026-10-30
Left for the model160.00 GiB
Memory bandwidth273 GB/s
Models that fit25 / 28
Heaviest model it takesdeepseek-v4-flash
160.00 GiB

Left for the model

Estimated

273 GB/s

Memory bandwidth

Estimated

25 / 28

Models that fit

Measured by Local AI Scope

Videos

Videos: PC with Ryzen AI Max+ PRO 495 and 192 GB unified 2

The official videos we found most useful. Press play and it opens right here.

The videos live on YouTube, and nothing loads from there until you press play (no-cookie mode). The thumbnail is served by us.

Memory

The memory you can actually use

Unified memory is shared with the operating system and everything you have open. The reserve here is deliberately conservative; you can change it in the tool.

How the memory on the box turns into memory you can use
Memory GiB
Memory on the box 192
Reserved for the system −3.00
Beyond the limit the manufacturer sets for the GPU −29.00
Left for the model 160.00
What the PC with Ryzen AI Max+ PRO 495 and 192 GB unified really has free for a modelHorizontal bar of the 192 GiB of the PC with Ryzen AI Max+ PRO 495 and 192 GB unified, split into 32.0 GiB outside what the GPU can use, 127.3 GiB for the deepseek-v4-flash model, 1.4 GiB for the context and 31.3 GiB free.0192 GiBOutside GPU: 32.0 GiBOutside GPU32.0Model: 127.3 GiBModel127.3Context (8,192): 1.4 GiBContext (8,192) 1.4Headroom: 31.3 GiBHeadroom31.3
Of the 192 GiB the machine has, 32.0 GiB never reach the model. The bar shows deepseek-v4-flash at IQ4_XS, the largest of the 28 models in the dataset that still fits at a 8,192-token context, and the KV cache that context needs — computed layer by layer, not with the usual rule of thumb.

192 GB on the box, 160 for the model. AMD states that the Ryzen AI Max+ PRO 495 can dedicate up to 160 GB of its 192 GB to the graphics processor, and the graphics processor is what runs the model. So every figure on this page is computed with 160, not with the 189 that the box minus our system reserve would give. On Linux that limit is a driver setting that AMD documents as adjustable, but it publishes no maximum figure for it: we stick to the figure it does publish.

Speed

Memory bandwidth

Two different limits, and they are easy to mix up. While the model is writing its answer, bandwidth rules: every token means reading the weights it uses again — all of them in a dense model; in a mixture of experts, the shared layers plus only the active experts — so tokens per second is roughly bandwidth divided by that amount. While the model is reading your document, compute rules: the whole input is processed at once. That is why a laptop with no GPU can take minutes before the first word appears and then type at a tolerable pace.

273 GB/s — Derived, not published by the manufacturer · the manufacturer publishes the bus width but neither the memory speed nor the bandwidth. This figure is the usual arithmetic derivation () and we could not confirm it at source (Source).

Compute: 15.4 TFLOPS (estimate for this class of machine) — Estimated · the manufacturer does not publish this figure at all; ours is a conservative estimate, not a specification. The figures in this line do not all come from the same measure across machines, because each manufacturer publishes a different one. Compare them between machines only with that in mind.

Fit

Which models fit here, and which do not

Fitting means three things at once fit in the memory left over: the model file, its context memory, and the runtime’s working headroom. Context memory is computed from each model’s declared attention pattern layer by layer, not from the generic formula — which is why several models fit here that the generic formula would rule out.

Every measured model against this machine: size, whether it fits at each context, and the largest context it holds
Model Compression shown Model size 8k 32k 128k Largest context that fits
qwen3-1.7b Q4_K_M 1.03 GiB yes yes — 32k
qwen3-4b-2507 Q4_K_M 2.33 GiB yes yes yes 256k
gemma4-e2b Q4_K_M 2.89 GiB yes yes yes 128k
gemma4-e4b Q4_K_M 4.63 GiB yes yes yes 128k
qwen3-8b Q4_K_M 4.68 GiB yes yes — 32k
granite-4.2-8b Q4_K_M 4.98 GiB yes yes yes 128k
qwen3.5-9b Q4_K_M 5.29 GiB yes yes yes 256k
gemma4-12b Q4_K_M 6.63 GiB yes yes yes 256k
phi-4 Q4_K_M 8.43 GiB yes — — 16k
gpt-oss-20b Q4_K_M 10.83 GiB yes yes yes 128k
mistral-small-24b Q4_K_M 13.35 GiB yes yes yes 128k
qwen3.8-27b Q4_K_M 15.33 GiB yes yes yes 256k
muse-glimmer-30b Q4_K_M 15.61 GiB yes yes yes 128k
qwen3.6-27b Q4_K_M 15.66 GiB yes yes yes 256k
gemma4-26b-a4b Q4_K_M 15.78 GiB yes yes yes 256k
gemma4-31b Q4_K_M 17.07 GiB yes yes yes 256k
qwen3-coder-30b Q4_K_M 17.28 GiB yes yes yes 256k
qwen3.6-35b-a3b Q4_K_M 20.61 GiB yes yes yes 256k
flint-40b Q4_K_M 23.61 GiB yes yes yes 256k
nemotron-3.5-lightning-30b Q4_K_M 23.73 GiB yes yes yes 256k
gpt-oss-120b Q4_K_M 58.46 GiB yes yes yes 128k
llama4-scout-17b Q4_K_M 60.87 GiB yes yes yes 1024k
nemotron-3.5-super-120b Q4_K_M 65.29 GiB yes yes yes 1024k
qwen3.8-flash-next IQ4_XS 87.25 GiB yes yes yes 256k
deepseek-v4-flash IQ4_XS 127.28 GiB yes yes yes 256k
glm-5.3-flash Q4_K_M 187.04 GiB no no no —
glm-5.2 Q4_K_M 433.83 GiB no no no —
mistral-large-4 Q4_K_M 591.21 GiB no no no —

Sizes are the real published files at the reference compression, one step per row: Q4_K_M where the author publishes it, the nearest neighbour where they do not. Every row states which one it is showing. Q4_K_M is our quality floor: below it the loss is audible in the answers. A model that would only fit here at a harsher compression is listed as not fitting, on purpose. A dash in a context column means the model itself does not offer that context, so there is nothing to fit.

Models that fit — 25 of the 28 models measured

Models that do not fit — 3 of the 28 models measured

Willing to compress a bit more? Then not everything on this list is out of reach. In the 160.00 GiB of unified memory the manufacturer lets the GPU use, glm-5.3-flash runs at Q3_K_M (144.37 GiB) with up to 256k tokens of context. Below the compression in the table a model loses quality, and at Q3_K_M noticeably more; that is why our count sticks to the table.

The machines on either side

Price

Price and availability

What a machine costs decides as much as what fits inside it, so the price belongs on this page. What follows is only what the manufacturer publishes, with the market it applies to and the day it was read.

From $6,799 (United States), as published on 2026-10-09 (Source). Vendor declared

That is GMKtec’s EVO-X5 Pro with 192 GB and a 2 TB drive: the lowest price we found for this chip with 192 GB on a machine that is already shipping in the US (on 1 October it was $6,599). GMKtec’s European store sells the same configuration at €6,599, duty paid and shipped from its German warehouse; for orders placed from 16 October it expects to dispatch them between 20 and 30 November 2026. In its US store, on 30 October 2026 it showed the machine in stock with dispatch within 3 business days.

What we earn on this page

Nothing, today. There is no affiliate link on this page and no commercial agreement behind any figure on it. If a buying link ever appears here, it will be marked as such and the commission declared in this same block. Two rules do not change on that day: the ranking on this site is computed before commercial availability is applied, and «best» never means «pays most».

Our affiliate policy