gpt-oss-120b at Q4_K_M, 8,192 tokens
NVIDIA GeForce RTX 4090
vs AMD Ryzen AI Max+ 395 with Radeon 8060S
Side by side · gpt-oss-120b at Q4_K_M, 8,192 tokens
| Property | NVIDIA GeForce RTX 4090 | AMD Ryzen AI Max+ 395 with Radeon 8060S |
|---|---|---|
| Runs | does not run as set | fits in device memory |
| Decode | does not run | ~56 tok/sFaster than you read |
| Memory needed | 71.9 GB of 24.0 GB | 71.9 GB of 128.0 GB |
| Spare or short | short by 47.9 GB | 56.1 GB spare |
| Weights | 70.8 GB | 70.8 GB |
| KV cache | 0.31 GB | 0.31 GB |
| Memory bandwidth | 1008 GB/s | 256 GB/s |
NVIDIA GeForce RTX 4090
NO FITVerdictunvalidated
This configuration is 47.9 GB over the available memory. Offloading the overflow needs more system RAM than was declared.
Open in the calculator →AMD Ryzen AI Max+ 395 with Radeon 8060S
NOTHING TO FIXVerdictestimate
56.1 GB spare and ~56 tok/s — above the 30 tok/s this site treats as faster than reading.
Open in the calculator →Read this carefully
Both columns come from the same engine and the same published inputs, so the comparison is like for like. It is one model at one context length: change either and the answer can invert, which is what the calculator links above are for — each opens its side with the same model, device, format and context.
Decode figures are calibrated estimates from the published calibration, whose measured error is on the accuracy page.