Calculator
Can I run it?
Choose a model, a quant file and how much context you want to keep. Each machine is checked the same way as on its own page: the file, plus context memory, plus 1.5 GB of overhead, against the memory its GPU can use.
Needs 60.2 GB = 58.5 GB file + 0.3 GB context + 1.5 GB overhead context memory estimated · 23 of 36 machines hold it without raising a limit · all about gpt-oss-120b
| Machine | Fit | Price | Generation |
|---|---|---|---|
| Dell Pro Precision with GB300NVIDIA workstation | Fits | ~$159,283 | ~1,222–1,561 tok/sestimate |
| 2x RTX 5090Multi-GPU | Fits | ~$4,109 + unpriced parts | ~163–238 tok/sestimate |
| Dell Pro Max Tower T2 with NVIDIA RTX PRO 6000 BlackwellNVIDIA workstation | Fits | ~$13,909 | 202 tok/smedian of 4 runs |
| 1x RTX PRO 6000 BlackwellSingle GPU | Fits | ~$20,833 | 202 tok/smedian of 4 runs |
| 4x Instinct MI50 32GB (used) on EPYC 7003Multi-GPU | Fits | ~$1,998 + unpriced parts | ~93–136 tok/sestimate |
| Apple Mac Studio (M5 Ultra, 80-core GPU)Apple unified memory | Fitsassumed limitfrom 96 GB | ~$6,799–$10,799 | 111 tok/smedian of 1 run |
| 4x RTX 3090 (used) on EPYC 7003, open frameMulti-GPU | Fits | ~$2,178 + unpriced parts | ~85–124 tok/sestimate |
| Apple Mac Studio (M5 Ultra, 64-core GPU)Apple unified memory | Fitsassumed limitfrom 96 GB | ~$5,499–$9,499 | 100 tok/smedian of 3 runs |
| Apple Mac Studio (M5 Max, 40-core GPU)Apple unified memory | Fitsassumed limitfrom 128 GB | ~$3,099–$5,099 | 90 tok/smedian of 4 runs |
| Apple MacBook Pro 14-inch (M5 Max, 40-core GPU)Apple unified memory | Fitsassumed limitfrom 128 GB | ~$4,699–$6,699 | 90 tok/smedian of 4 runs |
| Apple MacBook Pro 16-inch (M5 Max, 40-core GPU)Apple unified memory | Fitsassumed limitfrom 128 GB | ~$4,999–$6,999 | 90 tok/smedian of 4 runs |
| tiny corp tinybox red flashGPU desktop (prebuilt) | Fits | ~$22,000 | ~58–85 tok/sestimate |
| Framework Desktop (Ryzen AI Max+ PRO 495)AMD unified memory | Fitsassumed limit | ~$6,799 | ~47–60 tok/sestimate |
| NVIDIA DGX SparkNVIDIA GB10 | Fitsassumed limit | ~$4,699 | 53 tok/smedian of 23 runs |
| Dell Pro Precision with GB10NVIDIA GB10 | Fitsassumed limit | ~$5,523 | 53 tok/smedian of 23 runs |
| Framework Desktop (Ryzen AI Max+ 395)AMD unified memory | Fitsfrom 128 GB | ~$1,959–$3,449 | 52 tok/smedian of 5 runs |
| GMKtec EVO-X2 (Ryzen AI Max+ 395)AMD unified memory | Fitsfrom 128 GB | ~$2,600–$4,000 | 52 tok/smedian of 5 runs |
| Beelink GTR9 Pro (Ryzen AI Max+ 395)AMD unified memory | Fits | ~$4,699 | 52 tok/smedian of 5 runs |
| Minisforum MS-S1 MAX (Ryzen AI Max+ 395)AMD unified memory | Fits | ~$4,899 | 52 tok/smedian of 5 runs |
| Corsair AI Workstation 300 (Ryzen AI Max+ 395)AMD unified memory | Fits | ~$4,800 | 52 tok/smedian of 5 runs |
| HP Z2 Mini G1a (Ryzen AI Max+ PRO 395)AMD unified memory | Fits | ~$4,999 | 52 tok/smedian of 5 runs |
| Microsoft Surface RTX Spark Dev BoxOther | Fitsassumed limit | ~$6,000 | – |
| EPYC 9355P + 768 GB 12-channel DDR5 (CPU only)CPU + RAM server | Fitsassumed limit | ~$3,663 + unpriced parts | – |
| RTX 5090 + EPYC 9355P with 768 GB DDR5 (MoE offload)Hybrid GPU + RAM | GPU + RAM offloadassumed limit | ~$3,763 + unpriced parts | ~85–124 tok/sestimate, part in RAM |
| RTX 3090 (used) + 128 GB DDR5 on AM5 (MoE offload)Hybrid GPU + RAM | GPU + RAM offloadassumed limit | ~$4,833 + unpriced parts | ~14–21 tok/sestimate, part in RAM |
| Apple Mac Studio (M5 Max, 32-core GPU)Apple unified memory | Does not fit | ~$2,499 | |
| Apple Mac mini (M5 Pro, 16-core GPU)Apple unified memory | Does not fit | ~$1,699–$2,699 | |
| Apple Mac mini (M5 Pro, 20-core GPU)Apple unified memory | Does not fit | ~$1,899–$2,899 | |
| Apple MacBook Pro 14-inch (M5 Max, 32-core GPU)Apple unified memory | Does not fit | ~$4,099 | |
| Apple MacBook Pro 16-inch (M5 Max, 32-core GPU)Apple unified memory | Does not fit | ~$4,399 | |
| Framework Desktop (Ryzen AI Max 385)AMD unified memory | Does not fit | ~$1,269 | |
| 1x RTX 3090 (used)Single GPU | Does not fit | ~$2,944 + unpriced parts | |
| 2x RTX 3090 (used)Multi-GPU | Does not fit | ~$3,639 + unpriced parts | |
| 1x RTX 5090Single GPU | Does not fit | ~$3,234 + unpriced parts | |
| 2x Radeon RX 7900 XTXMulti-GPU | Does not fit | ~$5,637 | |
| 2x Intel Arc Pro B60Multi-GPU | Does not fit | ~$4,367 |
Measured speeds are medians of single-user runs at the same bit width on the same chip or cards; they do not change with the context you pick here. Estimates come from memory bandwidth and are labelled. Assumed memory limits are explained on each machine’s page and in how we compare.